Source author record

Chunhua Shen

Chunhua Shen appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Computer Vision Machine Learning Artificial Intelligence Computation and Language eess.IV Computation Computational Engineering, Finance, and Science Graphics Numerical Analysis

Catalog footprint

What is connected

170works

9topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions and underutilize intermediate probabilistic representations. In this paper, we propose EvoToken-DLM, a novel diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions. EvoToken-DLM enables a progressive transition from masked states to discrete outputs, supporting revisable decoding. To effectively support this evolution, we introduce continuous trajectory supervision, which aligns training objectives with iterative probabilistic updates. Extensive experiments across multiple benchmarks show that EvoToken-DLM consistently achieves superior performance, outperforming strong diffusion-based and masked DLM baselines. Project webpage: https://aim-uofa.github.io/EvoTokenDLM.

preprint2026arXiv

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple rewards by training one specialist model per reward, optimizing a weighted-sum reward $R(x)=\sum_k w_k R_k(x)$, or sequentially fine-tuning with a hand-crafted stage schedule. These approaches either fail to produce a unified model that can be jointly trained on all rewards or necessitates heavy manually tuned sequential training. We find that the failure stems from using a naive weighted-sum reward aggregation. This approach suffers from a sample-level mismatch because most rollouts are specialist samples, highly informative for certain reward dimensions but irrelevant for others; consequently, weighted summation dilutes their supervision. To address this issue, we propose MARBLE (Multi-Aspect Reward BaLancE), a gradient-space optimization framework that maintains independent advantage estimators for each reward, computes per-reward policy gradients, and harmonizes them into a single update direction without manually-tuned reward weighting, by solving a Quadratic Programming problem. We further propose an amortized formulation that exploits the affine structure of the loss used in DiffusionNFT, to reduce the per-step cost from K+1 backward passes to near single-reward baseline cost, together with EMA smoothing on the balancing coefficients to stabilize updates against transient single-batch fluctuations. On SD3.5 Medium with five rewards, MARBLE improves all five reward dimensions simultaneously, turns the worst-aligned reward's gradient cosine from negative under weighted summation in 80% of mini-batches to consistently positive, and runs at 0.97X the training speed of baseline training.

preprint2026arXiv

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of classical mechanics. While computer graphics and physics-based simulators can easily model such collisions using Newton formulas, modern pretrain-finetune paradigms discard the concept of object rigidity during pixel-level global denoising. Even perfectly correct mathematical constraints are treated as suboptimal solutions (i.e., conditions) during model optimization in post-training, fundamentally limiting the physical realism of generated videos. Motivated by these considerations, we introduce, for the first time, a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces, ensuring the physics knowledge is strictly applied rather than treated as conditions. Subsequently, we extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning while fully preserving the model's ability to leverage physics-grounded feedback. To validate our approach, we construct new benchmark PhysRVGBench and perform extensive qualitative and quantitative experiments to thoroughly assess its effectiveness.

preprint2024arXiv

Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models

Large-scale text-to-image diffusion models achieve unprecedented success in image generation and editing. However, how to extend such success to video editing is unclear. Recent initial attempts at video editing require significant text-to-video data and computation resources for training, which is often not accessible. In this work, we propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Our vid2vid-zero leverages off-the-shelf image diffusion models, and doesn't require training on any video. At the core of our method is a null-text inversion module for text-to-video alignment, a cross-frame modeling module for temporal consistency, and a spatial regularization module for fidelity to the original video. Without any training, we leverage the dynamic nature of the attention mechanism to enable bi-directional temporal modeling at test time. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos. Code is made available at \url{https://github.com/baaivision/vid2vid-zero}.

preprint2023arXiv

MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniques that are mobile-oriented, which comprises a set of language models at the scale of 1.4B and 2.7B parameters, trained from scratch, a multimodal vision model that is pre-trained in the CLIP fashion, cross-modality interaction via an efficient projector. We evaluate MobileVLM on several typical VLM benchmarks. Our models demonstrate on par performance compared with a few much larger models. More importantly, we measure the inference speed on both a Qualcomm Snapdragon 888 CPU and an NVIDIA Jeston Orin GPU, and we obtain state-of-the-art performance of 21.5 tokens and 65.3 tokens per second, respectively. Our code will be made available at: https://github.com/Meituan-AutoML/MobileVLM.

preprint2022arXiv

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is still under-explored. Although some works propose to either refine the trimaps or adapt the algorithms to real-world images via extra data augmentation, none of them has taken both into consideration, not to mention the significant performance deterioration on benchmarks while using those data augmentation. To fill this gap, we propose an image matting method which achieves higher robustness (RMat) via multilevel context assembling and strong data augmentation targeting matting. Specifically, we first build a strong matting framework by modeling ample global information with transformer blocks in the encoder, and focusing on details in combination with convolution layers as well as a low-level feature assembling attention block in the decoder. Then, based on this strong baseline, we analyze current data augmentation and explore simple but effective strong data augmentation to boost the baseline model and contribute a more generalizable matting method. Compared with previous methods, the proposed method not only achieves state-of-the-art results on the Composition-1k benchmark (11% improvement on SAD and 27% improvement on Grad) with smaller model size, but also shows more robust generalization results on other benchmarks, on real-world images, and also on varying coarse-to-fine trimaps with our extensive experiments.

preprint2022arXiv

Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection

Despite most existing anomaly detection studies assume the availability of normal training samples only, a few labeled anomaly examples are often available in many real-world applications, such as defect samples identified during random quality inspection, lesion images confirmed by radiologists in daily medical screening, etc. These anomaly examples provide valuable knowledge about the application-specific abnormality, enabling significantly improved detection of similar anomalies in some recent models. However, those anomalies seen during training often do not illustrate every possible class of anomaly, rendering these models ineffective in generalizing to unseen anomaly classes. This paper tackles open-set supervised anomaly detection, in which we learn detection models using the anomaly examples with the objective to detect both seen anomalies (`gray swans') and unseen anomalies (`black swans'). We propose a novel approach that learns disentangled representations of abnormalities illustrated by seen anomalies, pseudo anomalies, and latent residual anomalies (i.e., samples that have unusual residuals compared to the normal data in a latent space), with the last two abnormalities designed to detect unseen anomalies. Extensive experiments on nine real-world anomaly detection datasets show superior performance of our model in detecting seen and unseen anomalies under diverse settings. Code and data are available at: https://github.com/choubo/DRA.

preprint2022arXiv

DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

While self-supervised representation learning (SSL) has received widespread attention from the community, recent research argue that its performance will suffer a cliff fall when the model size decreases. The current method mainly relies on contrastive learning to train the network and in this work, we propose a simple yet effective Distilled Contrastive Learning (DisCo) to ease the issue by a large margin. Specifically, we find the final embedding obtained by the mainstream SSL methods contains the most fruitful information, and propose to distill the final embedding to maximally transmit a teacher's knowledge to a lightweight model by constraining the last embedding of the student to be consistent with that of the teacher. In addition, in the experiment, we find that there exists a phenomenon termed Distilling BottleNeck and present to enlarge the embedding dimension to alleviate this problem. Our method does not introduce any extra parameter to lightweight models during deployment. Experimental results demonstrate that our method achieves the state-of-the-art on all lightweight models. Particularly, when ResNet-101/ResNet-50 is used as teacher to teach EfficientNet-B0, the linear result of EfficientNet-B0 on ImageNet is very close to ResNet-101/ResNet-50, but the number of parameters of EfficientNet-B0 is only 9.4\%/16.3\% of ResNet-101/ResNet-50. Code is available at https://github. com/Yuting-Gao/DisCo-pytorch.

preprint2022arXiv

Efficient Decoder-free Object Detection with Transformers

Vision transformers (ViTs) are changing the landscape of object detection approaches. A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with the price of bringing considerable computation burden for inference. More subtle usage is the DETR family, which eliminates the need for many hand-designed components in object detection but introduces a decoder demanding an extra-long time to converge. As a result, transformer-based object detection can not prevail in large-scale applications. To overcome these issues, we propose a novel decoder-free fully transformer-based (DFFT) object detector, achieving high efficiency in both training and inference stages, for the first time. We simplify objection detection into an encoder-only single-level anchor-based dense prediction problem by centering around two entry points: 1) Eliminate the training-inefficient decoder and leverage two strong encoders to preserve the accuracy of single-level feature map prediction; 2) Explore low-level semantic features for the detection task with limited computational resources. In particular, we design a novel lightweight detection-oriented transformer backbone that efficiently captures low-level features with rich semantics based on a well-conceived ablation study. Extensive experiments on the MS COCO benchmark demonstrate that DFFT_SMALL outperforms DETR by 2.5% AP with 28% computation cost reduction and more than $10$x fewer training epochs. Compared with the cutting-edge anchor-based detector RetinaNet, DFFT_SMALL obtains over 5.5% AP gain while cutting down 70% computation cost.

preprint2022arXiv

Efficient Video Segmentation Models with Per-frame Inference

Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into account,e.g., by propagating the results to the neighboring frames using optical flow or extracting frame representations using multi-frame information, which may lead to inaccurate results or unbalanced latency. In this work, we focus on improving the temporal consistency without introducing computation overhead in inference. To this end, we perform inference at each frame. Temporal consistency is achieved by learning from video frames with extra constraints during the training phase. introduced for inference. We propose several techniques to learn from the video sequence, including a temporal consistency loss and online/offline knowledge distillation methods. On the task of semantic video segmentation, weighing among accuracy, temporal smoothness, and efficiency, our proposed method outperforms keyframe-based methods and a few baseline methods that are trained with each frame independently, on datasets including Cityscapes, Camvid, and 300VW-Mask. We further apply our training method to video instance segmentation on YouTubeVISand develop an application of portrait matting in video sequences, by segmenting temporally consistent instance-level trimaps across frames. Experiments show superior qualitative and quantitative results. Code is available at: https://git.io/vidseg.

preprint2022arXiv

End-to-End Video Text Spotting with Transformer

Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods typically follow the tracking-by-match paradigm and develop sophisticated pipelines. In this paper, rooted in Transformer sequence modeling, we propose a simple, but effective end-to-end video text DEtection, Tracking, and Recognition framework (TransDETR). TransDETR mainly includes two advantages: 1) Different from the explicit match paradigm in the adjacent frame, TransDETR tracks and recognizes each text implicitly by the different query termed text query over long-range temporal sequence (more than 7 frames). 2) TransDETR is the first end-to-end trainable video text spotting framework, which simultaneously addresses the three sub-tasks (e.g., text detection, tracking, recognition). Extensive experiments in four video text datasets (i.e.,ICDAR2013 Video, ICDAR2015 Video, Minetto, and YouTube Video Text) are conducted to demonstrate that TransDETR achieves state-of-the-art performance with up to around 8.0% improvements on video text spotting tasks. The code of TransDETR can be found at https://github.com/weijiawu/TransDETR.

preprint2022arXiv

FreeSOLO: Learning to Segment Objects without Annotations

Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and segmentation masks for learning. In this work, we propose a fully unsupervised learning method that learns class-agnostic instance segmentation without any annotations. We present FreeSOLO, a self-supervised instance segmentation framework built on top of the simple instance segmentation method SOLO. Our method also presents a novel localization-aware pre-training framework, where objects can be discovered from complicated scenes in an unsupervised manner. FreeSOLO achieves 9.8% AP_{50} on the challenging COCO dataset, which even outperforms several segmentation proposal methods that use manual annotations. For the first time, we demonstrate unsupervised class-agnostic instance segmentation successfully. FreeSOLO's box localization significantly outperforms state-of-the-art unsupervised object detection/discovery methods, with about 100% relative improvements in COCO AP. FreeSOLO further demonstrates superiority as a strong pre-training method, outperforming state-of-the-art self-supervised pre-training methods by +9.8% AP when fine-tuning instance segmentation with only 5% COCO masks. Code is available at: github.com/NVlabs/FreeSOLO

preprint2022arXiv

Improving Monocular Visual Odometry Using Learned Depth

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocular depth estimation module with a strong generalization capability for diverse scenes. It consists of two separate working modes to assist the localization and mapping. With a single monocular image input, the depth estimation module predicts a relative depth to help the localization module on improving the accuracy. With a sparse depth map and an RGB image input, the depth estimation module can generate accurate scale-consistent depth for dense mapping. Compared with current learning-based VO methods, our method demonstrates a stronger generalization ability to diverse scenes. More significantly, our framework is able to boost the performances of existing geometry-based VO methods by a large margin.

preprint2022arXiv

Instance and Panoptic Segmentation Using Conditional Convolutions

We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst (conditional convolutions for instance and panoptic segmentation). In the literature, top-performing instance segmentation methods typically follow the paradigm of Mask R-CNN and rely on ROI operations (typically ROIAlign) to attend to each instance. In contrast, we propose to attend to the instances with dynamic conditional convolutions. Instead of using instance-wise ROIs as inputs to the instance mask head of fixed weights, we design dynamic instance-aware mask heads, conditioned on the instances to be predicted. CondInst enjoys three advantages: 1.) Instance and panoptic segmentation are unified into a fully convolutional network, eliminating the need for ROI cropping and feature alignment. 2.) The elimination of the ROI cropping also significantly improves the output instance mask resolution. 3.) Due to the much improved capacity of dynamically-generated conditional convolutions, the mask head can be very compact (e.g., 3 conv. layers, each having only 8 channels), leading to significantly faster inference time per instance and making the overall inference time almost constant, irrelevant to the number of instances. We demonstrate a simpler method that can achieve improved accuracy and inference speed on both instance and panoptic segmentation tasks. On the COCO dataset, we outperform a few state-of-the-art methods. We hope that CondInst can be a strong baseline for instance and panoptic segmentation. Code is available at: https://git.io/AdelaiDet

preprint2022arXiv

PointAttN: You Only Need Attention for Point Cloud Completion

Point cloud completion referring to completing 3D shapes from partial 3D point clouds is a fundamental problem for 3D point cloud analysis tasks. Benefiting from the development of deep neural networks, researches on point cloud completion have made great progress in recent years. However, the explicit local region partition like kNNs involved in existing methods makes them sensitive to the density distribution of point clouds. Moreover, it serves limited receptive fields that prevent capturing features from long-range context information. To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for processing point cloud in a per-point manner to eliminate kNNs. Two essential blocks Geometric Details Perception (GDP) and Self-Feature Augment (SFA) are proposed to establish the short-range and long-range structural relationships directly among points in a simple yet effective way via attention mechanism. Then based on GDP and SFA, we construct a new framework with popular encoder-decoder architecture for point cloud completion. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes and predict complete point clouds with highly detailed geometries. Experimental results demonstrate that our PointAttN outperforms state-of-the-art methods by a large margin on popular benchmarks like Completion3D and PCN. Code is available at: https://github.com/ohhhyeahhh/PointAttN

preprint2022arXiv

PointInst3D: Segmenting 3D Instances by Points

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction fashion. In doing so it avoids the challenges that clustering-based methods face: introducing dependencies among different tasks of the model. We find the key to its success is assigning a suitable target to each sampled point. Instead of the commonly used static or distance-based assignment strategies, we propose to use an Optimal Transport approach to optimally assign target masks to the sampled points according to the dynamic matching costs. Our approach achieves promising results on both ScanNet and S3DIS benchmarks. The proposed approach removes intertask dependencies and thus represents a simpler and more flexible 3D instance segmentation framework than other competing methods, while achieving improved segmentation accuracy.

preprint2022arXiv

Poseur: Direct Human Pose Regression with Transformers

We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatmaps. This approach avoids much of the complexity associated with heatmap-based approaches. To overcome the feature misalignment issues of previous regression-based methods, we propose an attention mechanism that adaptively attends to the features that are most relevant to the target keypoints, considerably improving the accuracy. Importantly, our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Experiments on MS-COCO and MPII, two predominant pose-estimation datasets, demonstrate that our method significantly improves upon the state-of-the-art in regression-based pose estimation. More notably, ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.

preprint2022arXiv

PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining

Large-scale vision-language pre-training has achieved promising results on downstream tasks. Existing methods highly rely on the assumption that the image-text pairs crawled from the Internet are in perfect one-to-one correspondence. However, in real scenarios, this assumption can be difficult to hold: the text description, obtained by crawling the affiliated metadata of the image, often suffers from the semantic mismatch and the mutual compatibility. To address these issues, we introduce PyramidCLIP, which constructs an input pyramid with different semantic levels for each modality, and aligns visual elements and linguistic elements in the form of hierarchy via peer-level semantics alignment and cross-level relation alignment. Furthermore, we soften the loss of negative samples (unpaired samples) so as to weaken the strict constraint during the pre-training stage, thus mitigating the risk of forcing the model to distinguish compatible negative pairs. Experiments on five downstream tasks demonstrate the effectiveness of the proposed PyramidCLIP. In particular, with the same amount of 15 million pre-training image-text pairs, PyramidCLIP exceeds CLIP on ImageNet zero-shot classification top-1 accuracy by 10.6%/13.2%/10.0% with ResNet50/ViT-B32/ViT-B16 based image encoder respectively. When scaling to larger datasets, PyramidCLIP achieves the state-of-the-art results on several downstream tasks. In particular, the results of PyramidCLIP-ResNet50 trained on 143M image-text pairs surpass that of CLIP using 400M data on ImageNet zero-shot classification task, significantly improving the data efficiency of CLIP.

preprint2022arXiv

Real-time End-to-End Video Text Spotter with Contrastive Representation Learning

Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models long-range dependencies and learning temporal information across multiple frames. 3) A simple, lightweight architecture is designed for effective and accurate performance, including GPU-parallel detection post-processing, CTC-based recognition head with Masked RoI. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting IDF1 of 72.0% at 41.0 FPS on ICDAR2015video, with 10.5% and 32.0 FPS improvement the previous best method. The code can be found at github.com/weijiawu/CoText.

preprint2022arXiv

Retrieval Augmented Classification for Long-Tail Visual Recognition

We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module. RAC consists of a standard base image encoder fused with a parallel retrieval branch that queries a non-parametric external memory of pre-encoded images and associated text snippets. We apply RAC to the problem of long-tail classification and demonstrate a significant improvement over previous state-of-the-art on Places365-LT and iNaturalist-2018 (14.5% and 6.7% respectively), despite using only the training datasets themselves as the external information source. We demonstrate that RAC's retrieval module, without prompting, learns a high level of accuracy on tail classes. This, in turn, frees the base encoder to focus on common classes, and improve its performance thereon. RAC represents an alternative approach to utilizing large, pretrained models without requiring fine-tuning, as well as a first step towards more effectively making use of external memory within common computer vision architectures.

preprint2022arXiv

SPTS: Single-Point Text Spotting

Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level bounding boxes). For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance. We propose an end-to-end scene text spotting method that tackles scene text spotting as a sequence prediction task. Given an image as input, we formulate the desired detection and recognition results as a sequence of discrete tokens and use an auto-regressive Transformer to predict the sequence. The proposed method is simple yet effective, which can achieve state-of-the-art results on widely used benchmarks. Most significantly, we show that the performance is not very sensitive to the positions of the point annotation, meaning that it can be much easier to be annotated or even be automatically generated than the bounding box that requires precise positions. We believe that such a pioneer attempt indicates a significant opportunity for scene text spotting applications of a much larger scale than previously possible. The code is available at https://github.com/shannanyinxiang/SPTS.

preprint2022arXiv

Structured Binary Neural Networks for Image Recognition

We propose methods to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models that are specifically friendly to mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs often seek to approximate the floating-point information using a set of discrete values, which we call value approximation, typically assuming the same architecture as the full-precision networks. Here we take a novel "structure approximation" view of quantization -- it is very likely that different architectures designed for low-bit networks may be better for achieving good performance. In particular, we propose a "network decomposition" strategy, termed Group-Net, in which we divide the network into groups. Thus, each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches. In addition, we learn effective connections among groups to improve the representation capability. Moreover, the proposed Group-Net shows strong generalization to other tasks. For instance, we extend Group-Net for accurate semantic segmentation by embedding rich context into the binary structure. Furthermore, for the first time, we apply binary neural networks to object detection. Experiments on both classification, semantic segmentation and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature. Our methods outperform the previous best binary neural networks in terms of accuracy and computation efficiency.

preprint2022arXiv

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named \textbf{To}ken \textbf{P}yramid Vision Trans\textbf{former} (\textbf{TopFormer}). The proposed \textbf{TopFormer} takes Tokens from various scales as input to produce scale-aware semantic features, which are then injected into the corresponding tokens to augment the representation. Experimental results demonstrate that our method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency. On the ADE20K dataset, TopFormer achieves 5\% higher accuracy in mIoU than MobileNetV3 with lower latency on an ARM-based mobile device. Furthermore, the tiny version of TopFormer achieves real-time inference on an ARM-based mobile device with competitive results. The code and models are available at: https://github.com/hustvl/TopFormer

preprint2022arXiv

Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching

The development of scene text recognition (STR) in the era of deep learning has been mainly focused on novel architectures of STR models. However, training protocol (i.e., settings of the hyper-parameters involved in the training of STR models), which plays an equally important role in successfully training a good STR model, is under-explored for scene text recognition. In this work, we attempt to improve the accuracy of existing STR models by searching for optimal training protocol. Specifically, we develop a training protocol search algorithm, based on a newly designed search space and an efficient search algorithm using evolutionary optimization and proxy tasks. Experimental results show that our searched training protocol can improve the recognition accuracy of mainstream STR models by 2.7%~3.9%. In particular, with the searched training protocol, TRBA-Net achieves 2.1% higher accuracy than the state-of-the-art STR model (i.e., EFIFSTR), while the inference speed is 2.3x and 3.7x faster on CPU and GPU respectively. Extensive experiments are conducted to demonstrate the effectiveness of the proposed method and the generalization ability of the training protocol found by our search method. Code is available at https://github.com/VDIGPKU/STR_TPSearch.

preprint2022arXiv

TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convolutional neural networks. Compared to iteration based saliency methods, single backward pass based saliency methods benefit from faster speed, and they are widely used in downstream visual tasks. Thus, we focus on single backward pass based methods. However, existing methods in this category struggle to uccessfully produce fine-grained saliency maps concentrating on specific target classes. That said, producing faithful saliency maps satisfying both target-selectiveness and fine-grainedness using a single backward pass is a challenging problem in the field. To mitigate this problem, we revisit the gradient flow inside the network, and find that the entangled semantics and original weights may disturb the propagation of target-relevant saliency. Inspired by those observations, we propose a novel visual saliency method, termed Target-Selective Gradient Backprop (TSGB), which leverages rectification operations to effectively emphasize target classes and further efficiently propagate the saliency to the image space, thereby generating target-selective and fine-grained saliency maps. The proposed TSGB consists of two components, namely, TSGB-Conv and TSGB-FC, which rectify the gradients for convolutional layers and fully-connected layers, respectively. Extensive qualitative and quantitative experiments on the ImageNet and Pascal VOC datasets show that the proposed method achieves more accurate and reliable results than the other competitive methods. Code is available at https://github.com/123fxdx/CNNvisualizationTSGB.

preprint2021arXiv

CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation

Convolutional neural networks (CNNs) have been the de facto standard for nowadays 3D medical image segmentation. The convolutional operations used in these networks, however, inevitably have limitations in modeling the long-range dependency due to their inductive bias of locality and weight sharing. Although Transformer was born to address this issue, it suffers from extreme computational and spatial complexities in processing high-resolution 3D feature maps. In this paper, we propose a novel framework that efficiently bridges a {\bf Co}nvolutional neural network and a {\bf Tr}ansformer {\bf (CoTr)} for accurate 3D medical image segmentation. Under this framework, the CNN is constructed to extract feature representations and an efficient deformable Transformer (DeTrans) is built to model the long-range dependency on the extracted feature maps. Different from the vanilla Transformer which treats all image positions equally, our DeTrans pays attention only to a small set of key positions by introducing the deformable self-attention mechanism. Thus, the computational and spatial complexities of DeTrans have been greatly reduced, making it possible to process the multi-scale and high-resolution feature maps, which are usually of paramount importance for image segmentation. We conduct an extensive evaluation on the Multi-Atlas Labeling Beyond the Cranial Vault (BCV) dataset that covers 11 major human organs. The results indicate that our CoTr leads to a substantial performance improvement over other CNN-based, transformer-based, and hybrid methods on the 3D multi-organ segmentation task. Code is available at \def\UrlFont{\rm\small\ttfamily} \url{https://github.com/YtongXie/CoTr}

preprint2021arXiv

DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions. The inevitable variation in the instance scales can lead bottom-up methods to become particularly sensitive to hyper-parameter values. To this end, we propose instead a dynamic, proposal-free, data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. To make the kernels discriminative, we explore a large context by gathering homogeneous points that share identical semantic categories and have close votes for the geometric centroids. Instances are then decoded by several simple convolutional layers. Due to the limited receptive field introduced by the sparse convolution, a small light-weight transformer is also devised to capture the long-range dependencies and high-level interactions among point samples. The proposed method achieves promising results on both ScanetNetV2 and S3DIS, and this performance is robust to the particular hyper-parameter values chosen. It also improves inference speed by more than 25% over the current state-of-the-art. Code is available at: https://git.io/DyCo3D

preprint2021arXiv

Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection

Multi-orientation scene text detection has recently gained significant research attention. Previous methods directly predict words or text lines, typically by using quadrilateral shapes. However, many of these methods neglect the significance of consistent labeling, which is important for maintaining a stable training process, especially when it comprises a large amount of data. Here we solve this problem by proposing a new method, Orderless Box Discretization (OBD), which first discretizes the quadrilateral box into several key edges containing all potential horizontal and vertical positions. To decode accurate vertex positions, a simple yet effective matching procedure is proposed for reconstructing the quadrilateral bounding boxes. Our method solves the ambiguity issue, which has a significant impact on the learning process. Extensive ablation studies are conducted to validate the effectiveness of our proposed method quantitatively. More importantly, based on OBD, we provide a detailed analysis of the impact of a collection of refinements, which may inspire others to build state-of-the-art text detectors. Combining both OBD and these useful refinements, we achieve state-of-the-art performance on various benchmarks, including ICDAR 2015 and MLT. Our method also won the first place in the text detection task at the recent ICDAR2019 Robust Reading Challenge for Reading Chinese Text on Signboards, further demonstrating its superior performance. The code is available at https://git.io/TextDet.

preprint2021arXiv

Object Detection Made Simpler by Eliminating Heuristic NMS

We show a simple NMS-free, end-to-end object detection framework, of which the network is a minimal modification to a one-stage object detector such as the FCOS detection model [Tian et al. 2019]. We attain on par or even improved detection accuracy compared with the original one-stage detector. It performs detection at almost the same inference speed, while being even simpler in that now the post-processing NMS (non-maximum suppression) is eliminated during inference. If the network is capable of identifying only one positive sample for prediction for each ground-truth object instance in an image, then NMS would become unnecessary. This is made possible by attaching a compact PSS head for automatic selection of the single positive sample for each instance (see Fig. 1). As the learning objective involves both one-to-many and one-to-one label assignments, there is a conflict in the labels of some training examples, making the learning challenging. We show that by employing a stop-gradient operation, we can successfully tackle this issue and train the detector. On the COCO dataset, our simple design achieves superior performance compared to both the FCOS baseline detector with NMS post-processing and the recent end-to-end NMS-free detectors. Our extensive ablation studies justify the rationale of the design choices.

preprint2020arXiv

A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification

Automated skin lesion segmentation and classification are two most essential and related tasks in the computer-aided diagnosis of skin cancer. Despite their prevalence, deep learning models are usually designed for only one task, ignoring the potential benefits in jointly performing both tasks. In this paper, we propose the mutual bootstrapping deep convolutional neural networks (MB-DCNN) model for simultaneous skin lesion segmentation and classification. This model consists of a coarse segmentation network (coarse-SN), a mask-guided classification network (mask-CN), and an enhanced segmentation network (enhanced-SN). On one hand, the coarse-SN generates coarse lesion masks that provide a prior bootstrapping for mask-CN to help it locate and classify skin lesions accurately. On the other hand, the lesion localization maps produced by mask-CN are then fed into enhanced-SN, aiming to transfer the localization information learned by mask-CN to enhanced-SN for accurate lesion segmentation. In this way, both segmentation and classification networks mutually transfer knowledge between each other and facilitate each other in a bootstrapping way. Meanwhile, we also design a novel rank loss and jointly use it with the Dice loss in segmentation networks to address the issues caused by class imbalance and hard-easy pixel imbalance. We evaluate the proposed MB-DCNN model on the ISIC-2017 and PH2 datasets, and achieve a Jaccard index of 80.4% and 89.4% in skin lesion segmentation and an average AUC of 93.8% and 97.7% in skin lesion classification, which are superior to the performance of representative state-of-the-art skin lesion segmentation and classification methods. Our results suggest that it is possible to boost the performance of skin lesion segmentation and classification simultaneously via training a unified model to perform both tasks in a mutual bootstrapping way.

preprint2020arXiv

A Robust Attentional Framework for License Plate Recognition in the Wild

Recognizing car license plates in natural scene images is an important yet still challenging task in realistic applications. Many existing approaches perform well for license plates collected under constrained conditions, eg, shooting in frontal and horizontal view-angles and under good lighting conditions. However, their performance drops significantly in an unconstrained environment that features rotation, distortion, occlusion, blurring, shading or extreme dark or bright conditions. In this work, we propose a robust framework for license plate recognition in the wild. It is composed of a tailored CycleGAN model for license plate image generation and an elaborate designed image-to-sequence network for plate recognition. On one hand, the CycleGAN based plate generation engine alleviates the exhausting human annotation work. Massive amount of training data can be obtained with a more balanced character distribution and various shooting conditions, which helps to boost the recognition accuracy to a large extent. On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly. Without using any heuristics rule or post-processing, our method achieves the state-of-the-art performance on four public datasets, which demonstrates the generality and robustness of our framework. Moreover, we released a new license plate dataset, named "CLPD", with 1200 images from all 31 provinces in mainland China. The dataset can be available from: https://github.com/wangpengnorman/CLPD_dataset.

preprint2020arXiv

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

Scene text detection and recognition has received increasing research attention. Existing methods can be roughly categorized into two groups: character-based and segmentation-based. These methods either are costly for character annotation or need to maintain a complex pipeline, which is often not suitable for real-time applications. Here we address the problem by proposing the Adaptive Bezier-Curve Network (ABCNet). Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve. 2) We design a novel BezierAlign layer for extracting accurate convolution features of a text instance with arbitrary shapes, significantly improving the precision compared with previous methods. 3) Compared with standard bounding box detection, our Bezier curve detection introduces negligible computation overhead, resulting in superiority of our method in both efficiency and accuracy. Experiments on arbitrarily-shaped benchmark datasets, namely Total-Text and CTW1500, demonstrate that ABCNet achieves state-of-the-art accuracy, meanwhile significantly improving the speed. In particular, on Total-Text, our realtime version is over 10 times faster than recent state-of-the-art methods with a competitive recognition accuracy. Code is available at https://tinyurl.com/AdelaiDet

preprint2020arXiv

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation

The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable accuracy decrease. We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation. To this end, we propose an efficient and effective architecture with a good trade-off between speed and accuracy, termed Bilateral Segmentation Network (BiSeNet V2). This architecture involves: (i) a Detail Branch, with wide channels and shallow layers to capture low-level details and generate high-resolution feature representation; (ii) a Semantic Branch, with narrow channels and deep layers to obtain high-level semantic context. The Semantic Branch is lightweight due to reducing the channel capacity and a fast-downsampling strategy. Furthermore, we design a Guided Aggregation Layer to enhance mutual connections and fuse both types of feature representation. Besides, a booster training strategy is designed to improve the segmentation performance without any extra inference cost. Extensive quantitative and qualitative evaluations demonstrate that the proposed architecture performs favourably against a few state-of-the-art real-time semantic segmentation approaches. Specifically, for a 2,048x1,024 input, we achieve 72.6% Mean IoU on the Cityscapes test set with a speed of 156 FPS on one NVIDIA GeForce GTX 1080 Ti card, which is significantly faster than existing methods, yet we achieve better segmentation accuracy.

preprint2020arXiv

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and more efficient than two-stage approaches like Mask R-CNN. To date, almost all such approaches fall behind the two-stage Mask R-CNN method in mask precision when models have similar computation complexity, leaving great room for improvement. In this work, we achieve improved mask prediction by effectively combining instance-level information with semantic information with lower-level fine-granularity. Our main contribution is a blender module which draws inspiration from both top-down and bottom-up instance segmentation approaches. The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference. BlendMask can be easily incorporated with the state-of-the-art one-stage detection frameworks and outperforms Mask R-CNN under the same training schedule while being 20% faster. A light-weight version of BlendMask achieves $ 34.2% $ mAP at 25 FPS evaluated on a single 1080Ti GPU card. Because of its simplicity and efficacy, we hope that our BlendMask could serve as a simple yet strong baseline for a wide range of instance-wise prediction tasks. Code is available at https://git.io/AdelaiDet

preprint2020arXiv

Conditional Convolutions for Instance Segmentation

We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation). Top-performing instance segmentation methods such as Mask R-CNN rely on ROI operations (typically ROIPool or ROIAlign) to obtain the final instance masks. In contrast, we propose to solve instance segmentation from a new perspective. Instead of using instance-wise ROIs as inputs to a network of fixed weights, we employ dynamic instance-aware networks, conditioned on instances. CondInst enjoys two advantages: 1) Instance segmentation is solved by a fully convolutional network, eliminating the need for ROI cropping and feature alignment. 2) Due to the much improved capacity of dynamically-generated conditional convolutions, the mask head can be very compact (e.g., 3 conv. layers, each having only 8 channels), leading to significantly faster inference. We demonstrate a simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed. On the COCO dataset, we outperform a few recent methods including well-tuned Mask RCNN baselines, without longer training schedules needed. Code is available: https://github.com/aim-uofa/adet

preprint2020arXiv

Context Prior for Scene Segmentation

Recent works have widely explored the contextual dependencies to achieve more accurate segmentation results. However, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding. In this work, we directly supervise the feature aggregation to distinguish the intra-class and inter-class context clearly. Specifically, we develop a Context Prior with the supervision of the Affinity Loss. Given an input image and corresponding ground truth, Affinity Loss constructs an ideal affinity map to supervise the learning of Context Prior. The learned Context Prior extracts the pixels belonging to the same category, while the reversed prior focuses on the pixels of different classes. Embedded into a conventional deep CNN, the proposed Context Prior Layer can selectively capture the intra-class and inter-class contextual dependencies, leading to robust feature representation. To validate the effectiveness, we design an effective Context Prior Network (CPNet). Extensive quantitative and qualitative evaluations demonstrate that the proposed model performs favorably against state-of-the-art semantic segmentation approaches. More specifically, our algorithm achieves 46.3% mIoU on ADE20K, 53.9% mIoU on PASCAL-Context, and 81.3% mIoU on Cityscapes. Code is available at https://git.io/ContextPrior.

preprint2020arXiv

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or further) can enjoy better generalization, with the price of failing to recover the accurate geometric shape of the scene. In this work, we propose a dataset and methods to tackle this dilemma, aiming to predict accurate depth up to an affine transformation with good generalization to diverse scenes. First we construct a large-scale and diverse dataset, termed Diverse Scene Depth dataset (DiverseDepth), which has a broad range of scenes and foreground contents. Compared with previous learning objectives, i.e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes. Furthermore, in order to train the model on the complex dataset effectively, we propose a multi-curriculum learning method. Experiments show that our method outperforms previous methods on 8 datasets by a large margin with the zero-shot test setting, demonstrating the excellent generalization capacity of the learned model to diverse scenes. The reconstructed point clouds with the predicted depth show that our method can recover high-quality 3D shapes. Code and dataset are available at: https://tinyurl.com/DiverseDepth

preprint2020arXiv

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Scene text detection, an important step of scene text reading systems, has witnessed rapid development with convolutional neural networks. Nonetheless, two main challenges still exist and hamper its deployment to real-world applications. The first problem is the trade-off between speed and accuracy. The second one is to model the arbitrary-shaped text instance. Recently, some methods have been proposed to tackle arbitrary-shaped text detection, but they rarely take the speed of the entire pipeline into consideration, which may fall short in practical applications.In this paper, we propose an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing. More specifically, the segmentation head is made up of Feature Pyramid Enhancement Module (FPEM) and Feature Fusion Module (FFM). FPEM is a cascadable U-shaped module, which can introduce multi-level information to guide the better segmentation. FFM can gather the features given by the FPEMs of different depths into a final feature for segmentation. The learnable post-processing is implemented by Pixel Aggregation (PA), which can precisely aggregate text pixels by predicted similarity vectors. Experiments on several standard benchmarks validate the superiority of the proposed PAN. It is worth noting that our method can achieve a competitive F-measure of 79.9% at 84.2 FPS on CTW1500.

preprint2020arXiv

Efficient Semantic Video Segmentation with Per-frame Inference

For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence, e.g., by propagating the results to the neighboring frames using optical flow, or extracting the frame representations with other frames, which may lead to inaccurate results or unbalanced latency. In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. Different from previous per-frame models, we explicitly consider the temporal consistency among frames as extra constraints during the training process and embed the temporal consistency into the segmentation network. Therefore, in the inference process, we can process each frame independently with no latency, and improve the temporal consistency with no extra computational cost and post-processing. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed. Our results outperform previous keyframe based methods with a better trade-off between the accuracy and the inference speed on popular benchmarks, including the Cityscapes and Camvid. The temporal consistency is also improved compared with corresponding baselines which are trained with each frame independently. Code is available at: https://tinyurl.com/segment-video

preprint2020arXiv

From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting

Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, inf) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this task in a regression manner, while they are prone to suffer from an unseen scene with counts out of the scope of the closed set. In fact, counting has an interesting and exclusive property---spatially decomposable. A dense region can always be divided until sub-region counts are within the previously observed closed set. We therefore introduce the idea of spatial divide-and-conquer (S-DC) that transforms open-set counting into a closed-set problem. This idea is implemented by a novel Supervised Spatial Divide-and-Conquer Network (SS-DCNet). Thus, SS-DCNet can only learn from a closed set but generalize well to open-set scenarios via S-DC. SS-DCNet is also efficient. To avoid repeatedly computing sub-region convolutional features, S-DC is executed on the feature map instead of on the input image. We provide theoretical analyses as well as a controlled experiment on toy data, demonstrating why closed-set modeling makes sense. Extensive experiments show that SS-DCNet achieves the state-of-the-art performance. Code and models are available at: https://tinyurl.com/SS-DCNet.

preprint2020arXiv

Improving Generative Adversarial Networks with Local Coordinate Coding

Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data. However, such latent distribution may incur difficulties in data sampling for GANs. In this paper, rather than sampling from the predefined prior distribution, we propose an LCCGAN model with local coordinate coding (LCC) to improve the performance of generating data. First, we propose an LCC sampling method in LCCGAN to sample meaningful points from the latent manifold. With the LCC sampling method, we can exploit the local information on the latent manifold and thus produce new data with promising quality. Second, we propose an improved version, namely LCCGAN++, by introducing a higher-order term in the generator approximation. This term is able to achieve better approximation and thus further improve the performance. More critically, we derive the generalization bound for both LCCGAN and LCCGAN++ and prove that a low-dimensional input is sufficient to achieve good generalization performance. Extensive experiments on four benchmark datasets demonstrate the superiority of the proposed method over existing GANs.

preprint2020arXiv

Index Network

We show that existing upsampling operators can be unified using the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can often recover boundary details considerably better than other upsampling operators such as bilinear interpolation. By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision. At the core of this framework is a new learnable module, termed Index Network (IndexNet), which dynamically generates indices conditioned on the feature map itself. IndexNet can be used as a plug-in applying to almost all off-the-shelf convolutional networks that have coupled downsampling and upsampling stages, giving the networks the ability to dynamically capture variations of local patterns. In particular, we instantiate and investigate five families of IndexNet and demonstrate their effectiveness on four dense prediction tasks, including image denoising, image matting, semantic segmentation, and monocular depth estimation. Code and models have been made available at: https://tinyurl.com/IndexNetV1

preprint2020arXiv

Joint Deep Learning of Facial Expression Synthesis and Recognition

Recently, deep learning based facial expression recognition (FER) methods have attracted considerable attention and they usually require large-scale labelled training data. Nonetheless, the publicly available facial expression databases typically contain a small amount of labelled data. In this paper, to overcome the above issue, we propose a novel joint deep learning of facial expression synthesis and recognition method for effective FER. More specifically, the proposed method involves a two-stage learning procedure. Firstly, a facial expression synthesis generative adversarial network (FESGAN) is pre-trained to generate facial images with different facial expressions. To increase the diversity of the training images, FESGAN is elaborately designed to generate images with new identities from a prior distribution. Secondly, an expression recognition network is jointly learned with the pre-trained FESGAN in a unified framework. In particular, the classification loss computed from the recognition network is used to simultaneously optimize the performance of both the recognition network and the generator of FESGAN. Moreover, in order to alleviate the problem of data bias between the real images and the synthetic images, we propose an intra-class loss with a novel real data-guided back-propagation (RDBP) algorithm to reduce the intra-class variations of images from the same class, which can significantly improve the final performance. Extensive experimental results on public facial expression databases demonstrate the superiority of the proposed method compared with several state-of-the-art FER methods.

preprint2020arXiv

Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation

3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and diversely, which appears as both category imbalance and pattern imbalance. As a result, deep networks can easily forget the non-dominant cases during the learning process, resulting in unsatisfactory performance. Although re-weighting can reduce the influence of the well-classified examples, they cannot handle the non-dominant patterns during the dynamic training. In this paper, we propose a memory-augmented network to learn and memorize the representative prototypes that cover diverse samples universally. Specifically, a memory module is introduced to alleviate the forgetting issue by recording the patterns seen in mini-batch training. The learned memory items consistently reflect the interpretable and meaningful information for both dominant and non-dominant categories and cases. The distorted observations and rare cases can thus be augmented by retrieving the stored prototypes, leading to better performances and generalization. Exhaustive experiments on the benchmarks, i.e. S3DIS and ScanNetV2, reflect the superiority of our method on both effectiveness and efficiency. Not only the overall accuracy but also nondominant classes have improved substantially.

preprint2020arXiv

Learning Deep Gradient Descent Optimization for Image Deconvolution

As an integral component of blind image deblurring, non-blind deconvolution removes image blur with a given blur kernel, which is essential but difficult due to the ill-posed nature of the inverse problem. The predominant approach is based on optimization subject to regularization functions that are either manually designed, or learned from examples. Existing learning based methods have shown superior restoration quality but are not practical enough due to their restricted and static model design. They solely focus on learning a prior and require to know the noise level for deconvolution. We address the gap between the optimization-based and learning-based approaches by learning a universal gradient descent optimizer. We propose a Recurrent Gradient Descent Network (RGDN) by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme. A hyper-parameter-free update unit shared across steps is used to generate updates from the current estimates, based on a convolutional neural network. By training on diverse examples, the Recurrent Gradient Descent Network learns an implicit image prior and a universal update rule through recursive supervision. The learned optimizer can be repeatedly used to improve the quality of diverse degenerated observations. The proposed method possesses strong interpretability and high generalization. Extensive experiments on synthetic benchmarks and challenging real-world images demonstrate that the proposed deep optimization method is effective and robust to produce favorable results as well as practical for real-world image deblurring applications.

preprint2020arXiv

Mask Encoding for Single Shot Instance Segmentation

To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN. In contrast, one-stage alternatives cannot compete with Mask R-CNN in mask AP, mainly due to the difficulty of compactly representing masks, making the design of one-stage methods very challenging. In this work, we propose a simple singleshot instance segmentation framework, termed mask encoding based instance segmentation (MEInst). Instead of predicting the two-dimensional mask directly, MEInst distills it into a compact and fixed-dimensional representation vector, which allows the instance segmentation task to be incorporated into one-stage bounding-box detectors and results in a simple yet efficient instance segmentation framework. The proposed one-stage MEInst achieves 36.4% in mask AP with single-model (ResNeXt-101-FPN backbone) and single-scale testing on the MS-COCO benchmark. We show that the much simpler and flexible one-stage instance segmentation method, can also achieve competitive performance. This framework can be easily adapted for other instance-level recognition tasks. Code is available at: https://git.io/AdelaiDet

preprint2020arXiv

Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory

Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervision in the target domain, it is crucial to identify the underlying similarity-and-dissimilarity relationships among the unlabelled samples in the target domain. In order to use the whole data relationships efficiently in mini-batch training, we apply a series of memory modules to maintain an up-to-date representation of the entire dataset. Unlike the simple exemplar memory in previous works, we propose a novel multi-level memory network (MMN) to discover multi-level complementary information in the target domain, relying on three memory modules, i.e., part-level memory, instance-level memory, and domain-level memory. The proposed memory modules store multi-level representations of the target domain, which capture both the fine-grained differences between images and the global structure for the holistic target domain. The three memory modules complement each other and systematically integrate multi-level supervision from bottom to up. Experiments on three datasets demonstrate that the multi-level memory modules cooperatively boost the unsupervised cross-domain Re-ID task, and the proposed MMN achieves competitive results.

preprint2020arXiv

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising

Recently, neural architecture search (NAS) methods have attracted much attention and outperformed manually designed architectures on a few high-level vision tasks. In this paper, we propose HiNAS (Hierarchical NAS), an effort towards employing NAS to automatically design effective neural network architectures for image denoising. HiNAS adopts gradient based search strategies and employs operations with adaptive receptive field to build an flexible hierarchical search space. During the search stage, HiNAS shares cells across different feature levels to save memory and employ an early stopping strategy to avoid the collapse issue in NAS, and considerably accelerate the search speed. The proposed HiNAS is both memory and computation efficient, which takes only about 4.5 hours for searching using a single GPU. We evaluate the effectiveness of our proposed HiNAS on two different datasets, namely an additive white Gaussian noise dataset BSD500, and a realistic noise dataset SIM1800. Experimental results show that the architecture found by HiNAS has fewer parameters and enjoys a faster inference speed, while achieving highly competitive performance compared with state-of-the-art methods. We also present analysis on the architectures found by NAS. HiNAS also shows good performance on experiments for image de-raining.

preprint2020arXiv

NAS-FCOS: Fast Neural Architecture Search for Object Detection

The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, although typically such algorithms need an excessive amount of computational resources, e.g., a few thousand GPU-days. To date, on challenging vision tasks such as object detection, NAS, especially fast versions of NAS, is less studied. Here we propose to search for the decoder structure of object detectors with search efficiency being taken into consideration. To be more specific, we aim to efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS, using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms and strategies for evaluating network quality, we are able to efficiently search a top-performing detection architecture within 4 days using 8 V100 GPUs. The discovered architecture surpasses state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and FCOS) by 1.5 to 3.5 points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS for object detection.

preprint2020arXiv

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are vulnerable to learning coincidental correlations in the data rather than deeper relations between image content and ideas expressed in language. We present a dataset that takes a step towards addressing this problem in that it contains questions expressed in two languages, and an evaluation process that co-opts a well understood image-based metric to reflect the method's ability to reason. Measuring reasoning directly encourages generalization by penalizing answers that are coincidentally correct. The dataset reflects the scene-text version of the VQA problem, and the reasoning evaluation can be seen as a text-based version of a referring expression challenge. Experiments and analysis are provided that show the value of the dataset.

preprint2020arXiv

Pairwise Relation Learning for Semi-supervised Gland Segmentation

Accurate and automated gland segmentation on histology tissue images is an essential but challenging task in the computer-aided diagnosis of adenocarcinoma. Despite their prevalence, deep learning models always require a myriad number of densely annotated training images, which are difficult to obtain due to extensive labor and associated expert costs related to histology image annotations. In this paper, we propose the pairwise relation-based semi-supervised (PRS^2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net). The S-Net is trained on labeled data for segmentation, and PR-Net is trained on both labeled and unlabeled data in an unsupervised way to enhance its image representation ability via exploiting the semantic consistency between each pair of images in the feature space. Since both networks share their encoders, the image representation ability learned by PR-Net can be transferred to S-Net to improve its segmentation performance. We also design the object-level Dice loss to address the issues caused by touching glands and combine it with other two loss functions for S-Net. We evaluated our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset. Our results not only demonstrate the effectiveness of the proposed PR-Net and object-level Dice loss, but also indicate that our PRS^2 model achieves the state-of-the-art gland segmentation performance on both benchmarks.

preprint2020arXiv

PolarMask: Single Shot Instance Segmentation with Polar Representation

In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used as a mask prediction module for instance segmentation, by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on challenging COCO dataset. For the first time, we demonstrate a much simpler and flexible instance segmentation framework achieving competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation tasks. Code is available at: github.com/xieenze/PolarMask.

preprint2020arXiv

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Deep Convolutional Neural Networks (DCNNs) have recently shown outstanding performance in semantic image segmentation. However, state-of-the-art DCNN-based semantic segmentation methods usually suffer from high computational complexity due to the use of complex network architectures. This greatly limits their applications in the real-world scenarios that require real-time processing. In this paper, we propose a real-time high-performance DCNN-based method for robust semantic segmentation of urban street scenes, which achieves a good trade-off between accuracy and speed. Specifically, a Lightweight Baseline Network with Atrous convolution and Attention (LBN-AA) is firstly used as our baseline network to efficiently obtain dense feature maps. Then, the Distinctive Atrous Spatial Pyramid Pooling (DASPP), which exploits the different sizes of pooling operations to encode the rich and distinctive semantic information, is developed to detect objects at multiple scales. Meanwhile, a Spatial detail-Preserving Network (SPN) with shallow convolutional layers is designed to generate high-resolution feature maps preserving the detailed spatial information. Finally, a simple but practical Feature Fusion Network (FFN) is used to effectively combine both shallow and deep features from the semantic branch (DASPP) and the spatial branch (SPN), respectively. Extensive experimental results show that the proposed method respectively achieves the accuracy of 73.6% and 68.0% mean Intersection over Union (mIoU) with the inference speed of 51.0 fps and 39.3 fps on the challenging Cityscapes and CamVid test datasets (by only using a single NVIDIA TITAN X card). This demonstrates that the proposed method offers excellent performance at the real-time speed for semantic segmentation of urban street scenes.

preprint2020arXiv

Real-time Image Smoothing via Iterative Least Squares

Edge-preserving image smoothing is a fundamental procedure for many computer vision and graphic applications. There is a tradeoff between the smoothing quality and the processing speed: the high smoothing quality usually requires a high computational cost which leads to the low processing speed. In this paper, we propose a new global optimization based method, named iterative least squares (ILS), for efficient edge-preserving image smoothing. Our approach can produce high-quality results but at a much lower computational cost. Comprehensive experiments demonstrate that the propose method can produce results with little visible artifacts. Moreover, the computation of ILS can be highly parallel, which can be easily accelerated through either multi-thread computing or the GPU hardware. With the acceleration of a GTX 1080 GPU, it is able to process images of 1080p resolution ($1920\times1080$) at the rate of 20fps for color images and 47fps for gray images. In addition, the ILS is flexible and can be modified to handle more applications that require different smoothing properties. Experimental results of several applications show the effectiveness and efficiency of the proposed method. The code is available at \url{https://github.com/wliusjtu/Real-time-Image-Smoothing-via-Iterative-Least-Squares}

preprint2020arXiv

Representative Graph Neural Network

Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. Instead of propagating the messages from all positions, our RepGraph layer computes the response of one node merely with a few representative nodes. The locations of representative nodes come from a learned spatial offset matrix. The RepGraph layer is flexible to integrate into many visual architectures and combine with other operations. With the application of semantic segmentation, without any bells and whistles, our RepGraph network can compete or perform favourably against the state-of-the-art methods on three challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the task of object detection, our RepGraph layer can also improve the performance on the COCO dataset compared to the non-local operation. Code is available at https://git.io/RepGraph.

preprint2020arXiv

REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments

One of the long-term challenges of robotics is to enable robots to interact with humans in the visual world via natural language, as humans are visual animals that communicate through language. Overcoming this challenge requires the ability to perform a wide variety of complex tasks in response to multifarious instructions from humans. In the hope that it might drive progress towards more flexible and powerful human interactions with robots, we propose a dataset of varied and complex robot tasks, described in natural language, in terms of objects visible in a large set of real images. Given an instruction, success requires navigating through a previously-unseen environment to identify an object. This represents a practical challenge, but one that closely reflects one of the core visual problems in robotics. Several state-of-the-art vision-and-language navigation, and referring-expression models are tested to verify the difficulty of this new task, but none of them show promising results because there are many fundamental differences between our task and previous ones. A novel Interactive Navigator-Pointer model is also proposed that provides a strong baseline on the task. The proposed model especially achieves the best performance on the unseen test split, but still leaves substantial room for improvement compared to the human performance.

preprint2020arXiv

Scene Text Image Super-Resolution in the Wild

Low-resolution text images are often seen in natural scenes such as documents captured by mobile phones. Recognizing low-resolution text images is challenging because they lose detailed content information, leading to poor recognition accuracy. An intuitive solution is to introduce super-resolution (SR) techniques as pre-processing. However, previous single image super-resolution (SISR) methods are trained on synthetic low-resolution images (e.g.Bicubic down-sampling), which is simple and not suitable for real low-resolution text recognition. To this end, we pro-pose a real scene text SR dataset, termed TextZoom. It contains paired real low-resolution and high-resolution images which are captured by cameras with different focal length in the wild. It is more authentic and challenging than synthetic data, as shown in Fig. 1. We argue improv-ing the recognition accuracy is the ultimate goal for Scene Text SR. In this purpose, a new Text Super-Resolution Network termed TSRN, with three novel modules is developed. (1) A sequential residual block is proposed to extract the sequential information of the text images. (2) A boundary-aware loss is designed to sharpen the character boundaries. (3) A central alignment module is proposed to relieve the misalignment problem in TextZoom. Extensive experiments on TextZoom demonstrate that our TSRN largely improves the recognition accuracy by over 13%of CRNN, and by nearly 9.0% of ASTER and MORAN compared to synthetic SR data. Furthermore, our TSRN clearly outperforms 7 state-of-the-art SR methods in boosting the recognition accuracy of LR images in TextZoom. For example, it outperforms LapSRN by over 5% and 8%on the recognition accuracy of ASTER and CRNN. Our results suggest that low-resolution text recognition in the wild is far from being solved, thus more research effort is needed.

preprint2020arXiv

Scope Head for Accurate Localization in Object Detection

Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the design difficulty in hand-crafted 2D anchor definition and the learning complexity in 1D direct location regression. To tackle these issues, in this paper, we propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. This approach quantizes the prediction space and employs a coarse-to-fine strategy for localization. It achieves superior flexibility as in the regression based anchor-free methods, while produces more precise prediction. Besides, an inherit anchor selection score is learned to indicate the localization quality of the detection result, and we propose to better represent the confidence of a detection box by combining the category-classification score and the anchor-selection score. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO

preprint2020arXiv

Segmenting Transparent Objects in the Wild

Transparent objects such as windows and bottles made by glass widely exist in the real world. Segmenting transparent objects is challenging because these objects have diverse appearance inherited from the image background, making them had similar appearance with their surroundings. Besides the technical difficulty of this task, only a few previous datasets were specially designed and collected to explore this task and most of the existing datasets have major drawbacks. They either possess limited sample size such as merely a thousand of images without manual annotations, or they generate all images by using computer graphics method (i.e. not real image). To address this important problem, this work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10,428 images of real scenarios with carefully manual annotations, which are 10 times larger than the existing datasets. The transparent objects in Trans10K are extremely challenging due to high diversity in scale, viewpoint and occlusion as shown in Fig. 1. To evaluate the effectiveness of Trans10K, we propose a novel boundary-aware segmentation method, termed TransLab, which exploits boundary as the clue to improve segmentation of transparent objects. Extensive experiments and ablation studies demonstrate the effectiveness of Trans10K and validate the practicality of learning object boundary in TransLab. For example, TransLab significantly outperforms 20 recent object segmentation methods based on deep learning, showing that this task is largely unsolved. We believe that both Trans10K and TransLab have important contributions to both the academia and industry, facilitating future researches and applications.

preprint2020arXiv

Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection

Video anomaly detection is of critical practical importance to a variety of real applications because it allows human attention to be focused on events that are likely to be of interest, in spite of an otherwise overwhelming volume of video. We show that applying self-trained deep ordinal regression to video anomaly detection overcomes two key limitations of existing methods, namely, 1) being highly dependent on manually labeled normal training data; and 2) sub-optimal feature learning. By formulating a surrogate two-class ordinal regression task we devise an end-to-end trainable video anomaly detection approach that enables joint representation learning and anomaly scoring without manually labeled normal/abnormal data. Experiments on eight real-world video scenes show that our proposed method outperforms state-of-the-art methods that require no labeled training data by a substantial margin, and enables easy and accurate localization of the identified anomalies. Furthermore, we demonstrate that our method offers effective human-in-the-loop anomaly detection which can be critical in applications where anomalies are rare and the false-negative cost is high.

preprint2020arXiv

Soft Expert Reward Learning for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires an agent to find a specified spot in an unseen environment by following natural language instructions. Dominant methods based on supervised learning clone expert's behaviours and thus perform better on seen environments, while showing restricted performance on unseen ones. Reinforcement Learning (RL) based models show better generalisation ability but have issues as well, requiring large amount of manual reward engineering is one of which. In this paper, we introduce a Soft Expert Reward Learning (SERL) model to overcome the reward engineering designing and generalisation problems of the VLN task. Our proposed method consists of two complementary components: Soft Expert Distillation (SED) module encourages agents to behave like an expert as much as possible, but in a soft fashion; Self Perceiving (SP) module targets at pushing the agent towards the final destination as fast as possible. Empirically, we evaluate our model on the VLN seen, unseen and test splits and the model outperforms the state-of-the-art methods on most of the evaluation metrics.

preprint2020arXiv

SOLO: Segmenting Objects by Locations

We present a new, embarrassingly simple approach to instance segmentation in images. Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that have made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-thensegment' strategy as used by Mask R-CNN, or predict category masks first then use clustering techniques to group pixels into individual instances. We view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location and size, thus nicely converting instance mask segmentation into a classification-solvable problem. Now instance segmentation is decomposed into two classification tasks. We demonstrate a much simpler and flexible instance segmentation framework with strong performance, achieving on par accuracy with Mask R-CNN and outperforming recent singleshot instance segmenters in accuracy. We hope that this very simple and strong framework can serve as a baseline for many instance-level recognition tasks besides instance segmentation.

preprint2020arXiv

StructBoost: Boosting Methods for Predicting Structured Output Variables

Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost. StructBoost supports nonlinear structured learning by combining a set of weak structured learners. As SSVM generalizes SVM, our StructBoost generalizes standard boosting approaches such as AdaBoost, or LPBoost to structured learning. The resulting optimization problem of StructBoost is more challenging than SSVM in the sense that it may involve exponentially many variables and constraints. In contrast, for SSVM one usually has an exponential number of constraints and a cutting-plane method is used. In order to efficiently solve StructBoost, we formulate an equivalent $ 1 $-slack formulation and solve it using a combination of cutting planes and column generation. We show the versatility and usefulness of StructBoost on a range of problems such as optimizing the tree loss for hierarchical multi-class classification, optimizing the Pascal overlap criterion for robust visual tracking and learning conditional random field parameters for image segmentation.

preprint2020arXiv

Structured Knowledge Distillation for Dense Prediction

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two structured distillation schemes: i) pair-wise distillation that distills the pair-wise similarities by building a static graph; and ii) holistic distillation that uses adversarial training to distill holistic knowledge. The effectiveness of our knowledge distillation approaches is demonstrated by experiments on three dense prediction tasks: semantic segmentation, depth estimation and object detection. Code is available at: https://git.io/StructKD

preprint2020arXiv

Template-Based Automatic Search of Compact Semantic Segmentation Architectures

Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest. Nevertheless, on more difficult domains, such as dense per-pixel classification, current automatic approaches are limited in their scope - due to their strong reliance on existing image classifiers they tend to search only for a handful of additional layers with discovered architectures still containing a large number of parameters. In contrast, in this work we propose a novel solution able to find light-weight and accurate segmentation architectures starting from only few blocks of a pre-trained classification network. To this end, we progressively build up a methodology that relies on templates of sets of operations, predicts which template and how many times should be applied at each step, while also generating the connectivity structure and downsampling factors. All these decisions are being made by a recurrent neural network that is rewarded based on the score of the emitted architecture on the holdout set and trained using reinforcement learning. One discovered architecture achieves 63.2% mean IoU on CamVid and 67.8% on CityScapes having only 270K parameters. Pre-trained models and the search code are available at https://github.com/DrSleep/nas-segm-pytorch.

preprint2020arXiv

To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions

Real-world visual data often exhibits a long-tailed distribution, where some ''head'' classes have a large number of samples, yet only a few samples are available for ''tail'' classes. Such imbalanced distribution causes a great challenge for learning a deep neural network, which can be boiled down into a dilemma: on the one hand, we prefer to increase the exposure of tail class samples to avoid the excessive dominance of head classes in the classifier training. On the other hand, oversampling tail classes makes the network prone to over-fitting, since head class samples are often consequently under-represented. To resolve this dilemma, in this paper, we propose a simple-yet-effective auxiliary learning approach. The key idea is to split a network into a classifier part and a feature extractor part, and then employ different training strategies for each part. Specifically, to promote the awareness of tail-classes, a class-balanced sampling scheme is utilised for training both the classifier and the feature extractor. For the feature extractor, we also introduce an auxiliary training task, which is to train a classifier under the regular random sampling scheme. In this way, the feature extractor is jointly trained from both sampling strategies and thus can take advantage of all training data and avoid the over-fitting issue. Apart from this basic auxiliary task, we further explore the benefit of using self-supervised learning as the auxiliary task. Without using any bells and whistles, our model achieves superior performance over the state-of-the-art solutions.

preprint2020arXiv

Training Quantized Neural Networks with a Full-precision Auxiliary Module

In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by training the low-precision network with a fullprecision auxiliary module. Specifically, during training, we construct a mix-precision network by augmenting the original low-precision network with the full precision auxiliary module. Then the augmented mix-precision network and the low-precision network are jointly optimized. This strategy creates additional full-precision routes to update the parameters of the low-precision model, thus making the gradient back-propagates more easily. At the inference time, we discard the auxiliary module without introducing any computational complexity to the low-precision network. We evaluate the proposed method on image classification and object detection over various quantization approaches and show consistent performance increase. In particular, we achieve near lossless performance to the full-precision model by using a 4-bit detector, which is of great practical value.

preprint2020arXiv

Unsupervised Representation Learning by Predicting Random Distances

Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption into unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications into critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space. Random mapping is a theoretically proven approach to obtain approximately preserved distances. To well predict these random distances, the representation learner is optimised to learn genuine class structures that are implicitly embedded in the randomly projected space. Empirical results on 19 real-world datasets show that our learned representations substantially outperform a few state-of-the-art competing methods in both anomaly detection and clustering tasks. Code is available at https://git.io/RDP

preprint2020arXiv

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

We formulate counting as a sequential decision problem and present a novel crowd counting model solvable by deep reinforcement learning. In contrast to existing counting models that directly output count values, we divide one-step estimation into a sequence of much easier and more tractable sub-decision problems. Such sequential decision nature corresponds exactly to a physical process in reality scale weighing. Inspired by scale weighing, we propose a novel 'counting scale' termed LibraNet where the count value is analogized by weight. By virtually placing a crowd image on one side of a scale, LibraNet (agent) sequentially learns to place appropriate weights on the other side to match the crowd count. At each step, LibraNet chooses one weight (action) from the weight box (the pre-defined action pool) according to the current crowd image features and weights placed on the scale pan (state). LibraNet is required to learn to balance the scale according to the feedback of the needle (Q values). We show that LibraNet exactly implements scale weighing by visualizing the decision process how LibraNet chooses actions. Extensive experiments demonstrate the effectiveness of our design choices and report state-of-the-art results on a few crowd counting benchmarks. We also demonstrate good cross-dataset generalization of LibraNet. Code and models are made available at: https://git.io/libranet

preprint2016arXiv

Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources

We propose a method for visual question answering which combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. This allows more complex questions to be answered using the predominant neural network-based approach than has previously been possible. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain the whole answer. The method constructs a textual representation of the semantic content of an image, and merges it with textual information sourced from a knowledge base, to develop a deeper understanding of the scene viewed. Priming a recurrent neural network with this combined information, and the submitted question, leads to a very flexible visual question answering approach. We are specifically able to answer questions posed in natural language, that refer to information not contained in the image. We demonstrate the effectiveness of our model on two publicly available datasets, Toronto COCO-QA and MS COCO-VQA and show that it produces the best reported results in both cases.

preprint2016arXiv

Attend in groups: a weakly-supervised deep learning framework for learning from web data

Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to obtain, but direct training on such automatically harvested images can lead to unsatisfactory performance, because the noisy labels of Web images adversely affect the learned recognition models. To address this drawback we propose an end-to-end weakly-supervised deep learning framework which is robust to the label noise in Web images. The proposed framework relies on two unified strategies -- random grouping and attention -- to effectively reduce the negative impact of noisy web image annotations. Specifically, random grouping stacks multiple images into a single training instance and thus increases the labeling accuracy at the instance level. Attention, on the other hand, suppresses the noisy signals from both incorrectly labeled images and less discriminative image regions. By conducting intensive experiments on two challenging datasets, including a newly collected fine-grained dataset with Web images of different car models, the superior performance of the proposed methods over competitive baselines is clearly demonstrated.

preprint2016arXiv

Bridging Category-level and Instance-level Semantic Image Segmentation

We propose an approach to instance-level image segmentation that is built on top of category-level segmentation. Specifically, for each pixel in a semantic category mask, its corresponding instance bounding box is predicted using a deep fully convolutional regression network. Thus it follows a different pipeline to the popular detect-then-segment approaches that first predict instances' bounding boxes, which are the current state-of-the-art in instance segmentation. We show that, by leveraging the strength of our state-of-the-art semantic segmentation models, the proposed method can achieve comparable or even better results to detect-then-segment approaches. We make the following contributions. (i) First, we propose a simple yet effective approach to semantic instance segmentation. (ii) Second, we propose an online bootstrapping method during training, which is critically important for achieving good performance for both semantic category segmentation and instance-level segmentation. (iii) As the performance of semantic category segmentation has a significant impact on the instance-level segmentation, which is the second step of our approach, we train fully convolutional residual networks to achieve the best semantic category segmentation accuracy. On the PASCAL VOC 2012 dataset, we obtain the currently best mean intersection-over-union score of 79.1%. (iv) We also achieve state-of-the-art results for instance-level segmentation.

preprint2016arXiv

Cross-convolutional-layer Pooling for Image Recognition

Recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large image dataset can be used as a universal image descriptor, and that doing so leads to impressive performance for a variety of image classification tasks. Most of these studies adopt activations from a single DCNN layer, usually the fully-connected layer, as the image representation. In this paper, we proposed a novel way to extract image representations from two consecutive convolutional layers: one layer is utilized for local feature extraction and the other serves as guidance to pool the extracted features. By taking different viewpoints of convolutional layers, we further develop two schemes to realize this idea. The first one directly uses convolutional layers from a DCNN. The second one applies the pretrained CNN on densely sampled image regions and treats the fully-connected activations of each image region as convolutional feature activations. We then train another convolutional layer on top of that as the pooling-guidance convolutional layer. By applying our method to three popular visual classification tasks, we find our first scheme tends to perform better on the applications which need strong discrimination on subtle object patterns within small regions while the latter excels in the cases that require discrimination on category-level patterns. Overall, the proposed method achieves superior performance over existing ways of extracting image representations from a DCNN.

preprint2016arXiv

Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps

Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power of image representation is still an open problem. Conventional holistic features used in crowd counting often fail to capture semantic attributes and spatial cues of the image. In this paper, we propose integrating semantic information into learning locality-aware feature sets for accurate crowd counting. First, with the help of convolutional neural network (CNN), the original pixel space is mapped onto a dense attribute feature map, where each dimension of the pixel-wise feature indicates the probabilistic strength of a certain semantic class. Then, locality-aware features (LAF) built on the idea of spatial pyramids on neighboring patches are proposed to explore more spatial context and local information. Finally, the traditional VLAD encoding method is extended to a more generalized form in which diverse coefficient weights are taken into consideration. Experimental results validate the effectiveness of our presented method.

preprint2016arXiv

Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification

Person re-identification is to seek a correct match for a person of interest across views among a large number of imposters. It typically involves two procedures of non-linear feature extractions against dramatic appearance changes, and subsequent discriminative analysis in order to reduce intra- personal variations while enlarging inter-personal differences. In this paper, we introduce a hybrid architecture which combines Fisher vectors and deep neural networks to learn non-linear representations of person images to a space where data can be linearly separable. We reinforce a Linear Discriminant Analysis (LDA) on top of the deep neural network such that linearly separable latent representations can be learnt in an end-to-end fashion. By optimizing an objective function modified from LDA, the network is enforced to produce feature distributions which have a low variance within the same class and high variance between classes. The objective is essentially derived from the general LDA eigenvalue problem and allows to train the network with stochastic gradient descent and back-propagate LDA gradients to compute the gradients involved in Fisher vector encoding. For evaluation we test our approach on four benchmark data sets in person re-identification (VIPeR [1], CUHK03 [2], CUHK01 [3], and Market1501 [4]). Extensive experiments on these benchmarks show that our model can achieve state-of-the-art results.

preprint2016arXiv

Efficient piecewise training of deep structured models for semantic segmentation

Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information; specifically, we explore `patch-patch' context between image regions, and `patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to avoid repeated expensive CRF inference for back propagation. For capturing the patch-background context, we show that a network design with traditional multi-scale image input and sliding pyramid pooling is effective for improving performance. Our experimental results set new state-of-the-art performance on a number of popular semantic segmentation datasets, including NYUDv2, PASCAL VOC 2012, PASCAL-Context, and SIFT-flow. In particular, we achieve an intersection-over-union score of 78.0 on the challenging PASCAL VOC 2012 dataset.

preprint2016arXiv

Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentation

Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have facilitated easy acquisition of such depth information, the vast majority of images used in vision tasks do not contain depth information. In this paper, we show that augmenting RGB images with estimated depth can also improve the accuracy of both object detection and semantic segmentation. Specifically, we first exploit the recent success of depth estimation from monocular images and learn a deep depth estimation model. Then we learn deep depth features from the estimated depth and combine with RGB features for object detection and semantic segmentation. Additionally, we propose an RGB-D semantic segmentation method which applies a multi-task training scheme: semantic label prediction and depth value regression. We test our methods on several datasets and demonstrate that incorporating information from estimated depth improves the performance of object detection and semantic segmentation remarkably.

preprint2016arXiv

Fast Training of Triplet-based Deep Binary Embedding Networks

In this paper, we aim to learn a mapping (or embedding) from images to a compact binary space in which Hamming distances correspond to a ranking measure for the image retrieval task. We make use of a triplet loss because this has been shown to be most effective for ranking problems. However, training in previous works can be prohibitively expensive due to the fact that optimization is directly performed on the triplet space, where the number of possible triplets for training is cubic in the number of training examples. To address this issue, we propose to formulate high-order binary codes learning as a multi-label classification problem by explicitly separating learning into two interleaved stages. To solve the first stage, we design a large-scale high-order binary codes inference algorithm to reduce the high-order objective to a standard binary quadratic problem such that graph cuts can be used to efficiently infer the binary code which serve as the label of each training datum. In the second stage we propose to map the original image to compact binary codes via carefully designed deep convolutional neural networks (CNNs) and the hashing function fitting can be solved by training binary CNN classifiers. An incremental/interleaved optimization strategy is proffered to ensure that these two steps are interactive with each other during training for better accuracy. We conduct experiments on several benchmark datasets, which demonstrate both improved training time (by as much as two orders of magnitude) as well as producing state-of-the-art hashing for various retrieval tasks.

preprint2016arXiv

Hi Detector, What's Wrong with that Object? Identifying Irregular Object From Images by Modelling the Detection Score Distribution

In this work, we study the challenging problem of identifying the irregular status of objects from images in an "open world" setting, that is, distinguishing the irregular status of an object category from its regular status as well as objects from other categories in the absence of "irregular object" training data. To address this problem, we propose a novel approach by inspecting the distribution of the detection scores at multiple image regions based on the detector trained from the "regular object" and "other objects". The key observation motivating our approach is that for "regular object" images as well as "other objects" images, the region-level scores follow their own essential patterns in terms of both the score values and the spatial distributions while the detection scores obtained from an "irregular object" image tend to break these patterns. To model this distribution, we propose to use Gaussian Processes (GP) to construct two separate generative models for the case of the "regular object" and the "other objects". More specifically, we design a new covariance function to simultaneously model the detection score at a single region and the score dependencies at multiple regions. We finally demonstrate the superior performance of our method on a large dataset newly proposed in this paper.

preprint2016arXiv

High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks

We propose a method for high-performance semantic image segmentation (or semantic pixel labelling) based on very deep residual networks, which achieves the state-of-the-art performance. A few design factors are carefully considered to this end. We make the following contributions. (i) First, we evaluate different variations of a fully convolutional residual network so as to find the best configuration, including the number of layers, the resolution of feature maps, and the size of field-of-view. Our experiments show that further enlarging the field-of-view and increasing the resolution of feature maps are typically beneficial, which however inevitably leads to a higher demand for GPU memories. To walk around the limitation, we propose a new method to simulate a high resolution network with a low resolution network, which can be applied during training and/or testing. (ii) Second, we propose an online bootstrapping method for training. We demonstrate that online bootstrapping is critically important for achieving good accuracy. (iii) Third we apply the traditional dropout to some of the residual blocks, which further improves the performance. (iv) Finally, our method achieves the currently best mean intersection-over-union 78.3\% on the PASCAL VOC 2012 dataset, as well as on the recent dataset Cityscapes.

preprint2016arXiv

Image Captioning and Visual Question Answering Based on Attributes and External Knowledge

Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism can be used to incorporate external knowledge, which is critically important for answering high level visual questions. Specifically, we design a visual question answering model that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain a complete answer. Our final model achieves the best reported results on both image captioning and visual question answering on several benchmark datasets.

preprint2016arXiv

Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution

Given a set of images containing objects from the same category, the task of image co-localization is to identify and localize each instance. This paper shows that this problem can be solved by a simple but intriguing idea, that is, a common object detector can be learnt by making its detection confidence scores distributed like those of a strongly supervised detector. More specifically, we observe that given a set of object proposals extracted from an image that contains the object of interest, an accurate strongly supervised object detector should give high scores to only a small minority of proposals, and low scores to most of them. Thus, we devise an entropy-based objective function to enforce the above property when learning the common object detector. Once the detector is learnt, we resort to a segmentation approach to refine the localization. We show that despite its simplicity, our approach outperforms state-of-the-art methods.

preprint2016arXiv

Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

Image restoration, including image denoising, super resolution, inpainting, and so on, is a well-studied problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers. In other words, the network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers capture the abstraction of image contents while eliminating corruptions. Deconvolutional layers have the capability to upsample the feature maps and recover the image details. To deal with the problem that deeper networks tend to be more difficult to train, we propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains better results.

preprint2016arXiv

Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections

In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers act as the feature extractor, which capture the abstraction of image contents while eliminating noises/corruptions. De-convolutional layers are then used to recover the image details. We propose to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum. First, The skip connections allow the signal to be back-propagated to bottom layers directly, and thus tackles the problem of gradient vanishing, making training deep networks easier and achieving restoration performance gains consequently. Second, these skip connections pass image details from convolutional layers to de-convolutional layers, which is beneficial in recovering the original image. Significantly, with the large capacity, we can handle different levels of noises using a single model. Experimental results show that our network achieves better performance than all previously reported state-of-the-art methods.

preprint2016arXiv

Large-scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications

In computer vision, many problems such as image segmentation, pixel labelling, and scene parsing can be formulated as binary quadratic programs (BQPs). For submodular problems, cuts based methods can be employed to efficiently solve large-scale problems. However, general nonsubmodular problems are significantly more challenging to solve. Finding a solution when the problem is of large size to be of practical interest, however, typically requires relaxation. Two standard relaxation methods are widely used for solving general BQPs--spectral methods and semidefinite programming (SDP), each with their own advantages and disadvantages. Spectral relaxation is simple and easy to implement, but its bound is loose. Semidefinite relaxation has a tighter bound, but its computational complexity is high, especially for large scale problems. In this work, we present a new SDP formulation for BQPs, with two desirable properties. First, it has a similar relaxation bound to conventional SDP formulations. Second, compared with conventional SDP methods, the new SDP formulation leads to a significantly more efficient and scalable dual optimization approach, which has the same degree of complexity as spectral methods. We then propose two solvers, namely, quasi-Newton and smoothing Newton methods, for the dual problem. Both of them are significantly more efficiently than standard interior-point methods. In practice, the smoothing Newton solver is faster than the quasi-Newton solver for dense or medium-sized problems, while the quasi-Newton solver is preferable for large sparse/structured problems. Our experiments on a few computer vision applications including clustering, image segmentation, co-segmentation and registration show the potential of our SDP formulation for solving large-scale BQPs.

preprint2016arXiv

Less is more: zero-shot learning from online textual documents with noise suppression

Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Several recent works have pursued this approach by exploring various ways of connecting the visual and text domains. This paper revisits this idea by stepping further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This consideration motivates us to design a simple-but-effective zero-shot learning method capable of suppressing noise in the text. More specifically, we propose an $l_{2,1}$-norm based objective function which can simultaneously suppress the noisy signal in the text and learn a function to match the text document and visual features. We also develop an optimization algorithm to efficiently solve the resulting problem. By conducting experiments on two large datasets, we demonstrate that the proposed method significantly outperforms the competing methods which rely on online information sources but without explicit noise suppression. We further make an in-depth analysis of the proposed method and provide insight as to what kind of information in documents is useful for zero-shot learning.

preprint2016arXiv

Mining Mid-level Visual Patterns with Deep CNN Activations

The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative. Here we study this problem from the prospective of pattern mining while relying on the recently popularized Convolutional Neural Networks (CNNs). We observe that a fully-connected CNN activation extracted from an image patch typically possesses two appealing properties that enable its seamless integration with pattern mining techniques. The marriage between CNN activations and association rule mining, a well-known pattern mining technique in the literature, leads to fast and effective discovery of representative and discriminative patterns from a huge number of image patches. When we retrieve and visualize image patches with the same pattern, surprisingly, they are not only visually similar but also semantically consistent, and thus give rise to a mid-level visual element in our work. Given the patterns and retrieved mid-level visual elements, we propose two methods to generate image feature representations for each. The first method is to use the patterns as codewords in a dictionary, similar to the Bag-of-Visual-Words model, we compute a Bag-of-Patterns representation. The second one relies on the retrieved mid-level visual elements to construct a Bag-of-Elements representation. We evaluate the two encoding methods on scene and object classification tasks, and demonstrate that our approach outperforms or matches recent works using CNN activations for these tasks.

preprint2016arXiv

Order-aware Convolutional Pooling for Video Based Action Recognition

Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame. The pooling methods that they adopt, however, usually completely or partially neglect the dynamic information contained in the temporal domain, which may undermine the discriminative power of the resulting video representation since the video sequence order could unveil the evolution of a specific event or action. To overcome this drawback and explore the importance of incorporating the temporal order information, in this paper we propose a novel temporal pooling approach to aggregate the frame-level features. Inspired by the capacity of Convolutional Neural Networks (CNN) in making use of the internal structure of images for information abstraction, we propose to apply the temporal convolution operation to the frame-level representations to extract the dynamic information. However, directly implementing this idea on the original high-dimensional feature would inevitably result in parameter explosion. To tackle this problem, we view the temporal evolution of the feature value at each feature dimension as a 1D signal and learn a unique convolutional filter bank for each of these 1D signals. We conduct experiments on two challenging video-based action recognition datasets, HMDB51 and UCF101; and demonstrate that the proposed method is superior to the conventional pooling methods.

preprint2016arXiv

PersonNet: Person Re-identification with Deep Convolutional Neural Networks

In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification. The network takes a pair of raw RGB images as input, and outputs a similarity value indicating whether the two input images depict the same person. A layer of computing neighborhood range differences across two input images is employed to capture local relationship between patches. This operation is to seek a robust feature from input images. By increasing the depth to 10 weight layers and using very small (3$\times$3) convolution filters, our architecture achieves a remarkable improvement on the prior-art configurations. Meanwhile, an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into our architecture, which is beneficial to deep nets. Our method consistently outperforms state-of-the-art on two large datasets (CUHK03 and Market-1501), and a medium-sized data set (CUHK01).

preprint2016arXiv

Pushing the Limits of Deep CNNs for Pedestrian Detection

Compared to other applications in computer vision, convolutional neural networks have under-performed on pedestrian detection. A breakthrough was made very recently by using sophisticated deep CNN models, with a number of hand-crafted features, or explicit occlusion handling mechanism. In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labelling may be simply combined with a detector to boost the detection performance. By adding complementary hand-crafted features such as optical flow, the DCNN based detector can be further improved. We set a new record on the Caltech pedestrian dataset, lowering the log-average miss rate from $11.7\%$ to $8.9\%$, a relative improvement of $24\%$. We also achieve a comparable result to the state-of-the-art approaches on the KITTI dataset.

preprint2016arXiv

Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

In this work, we tackle the problem of car license plate detection and recognition in natural scene images. Inspired by the success of deep neural networks (DNNs) in various vision applications, here we leverage DNNs to learn high-level features in a cascade framework, which lead to improved performance on both detection and recognition. Firstly, we train a $37$-class convolutional neural network (CNN) to detect all characters in an image, which results in a high recall, compared with conventional approaches such as training a binary text/non-text classifier. False positives are then eliminated by the second plate/non-plate CNN classifier. Bounding box refinement is then carried out based on the edge information of the license plates, in order to improve the intersection-over-union (IoU) ratio. The proposed cascade framework extracts license plates effectively with both high recall and precision. Last, we propose to recognize the license characters as a {sequence labelling} problem. A recurrent neural network (RNN) with long short-term memory (LSTM) is trained to recognize the sequential features extracted from the whole license plate via CNNs. The main advantage of this approach is that it is segmentation free. By exploring context information and avoiding errors caused by segmentation, the RNN method performs better than a baseline method of combining segmentation and deep CNN classification; and achieves state-of-the-art recognition accuracy.

preprint2016arXiv

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. In this way, the deeper layers that capture high-level semantic features can be directly refined using fine-grained features from earlier convolutions. The individual components of RefineNet employ residual connections following the identity mapping mindset, which allows for effective end-to-end training. Further, we introduce chained residual pooling, which captures rich background context in an efficient manner. We carry out comprehensive experiments and set new state-of-the-art results on seven public datasets. In particular, we achieve an intersection-over-union score of 83.4 on the challenging PASCAL VOC 2012 dataset, which is the best reported result to date.

preprint2016arXiv

Sequential Person Recognition in Photo Albums with a Recurrent Network

Recognizing the identities of people in everyday photos is still a very challenging problem for machine vision, due to non-frontal faces, changes in clothing, location, lighting and similar. Recent studies have shown that rich relational information between people in the same photo can help in recognizing their identities. In this work, we propose to model the relational information between people as a sequence prediction task. At the core of our work is a novel recurrent network architecture, in which relational information between instances' labels and appearance are modeled jointly. In addition to relational cues, scene context is incorporated in our sequence prediction model with no additional cost. In this sense, our approach is a unified framework for modeling both contextual cues and visual appearance of person instances. Our model is trained end-to-end with a sequence of annotated instances in a photo as inputs, and a sequence of corresponding labels as targets. We demonstrate that this simple but elegant formulation achieves state-of-the-art performance on the newly released People In Photo Albums (PIPA) dataset.

preprint2016arXiv

Structured Learning of Binary Codes with Column Generation

Hashing methods aim to learn a set of hash functions which map the original features to compact binary codes with similarity preserving in the Hamming space. Hashing has proven a valuable tool for large-scale information retrieval. We propose a column generation based binary code learning framework for data-dependent hash function learning. Given a set of triplets that encode the pairwise similarity comparison information, our column generation based method learns hash functions that preserve the relative comparison relations within the large-margin learning framework. Our method iteratively learns the best hash functions during the column generation procedure. Existing hashing methods optimize over simple objectives such as the reconstruction error or graph Laplacian related loss functions, instead of the performance evaluation criteria of interest---multivariate performance measures such as the AUC and NDCG. Our column generation based method can be further generalized from the triplet loss to a general structured learning based framework that allows one to directly optimize multivariate performance measures. For optimizing general ranking measures, the resulting optimization problem can involve exponentially or infinitely many variables and constraints, which is more challenging than standard structured output learning. We use a combination of column generation and cutting-plane techniques to solve the optimization problem. To speed-up the training we further explore stage-wise training and propose to use a simplified NDCG loss for efficient inference. We demonstrate the generality of our method by applying it to ranking prediction and image retrieval, and show that it outperforms a few state-of-the-art hashing methods.

preprint2016arXiv

Structured learning of metric ensembles with application to person re-identification

Matching individuals across non-overlapping camera networks, known as person re-identification, is a fundamentally challenging problem due to the large visual appearance changes caused by variations of viewpoints, lighting, and occlusion. Approaches in literature can be categoried into two streams: The first stream is to develop reliable features against realistic conditions by combining several visual features in a pre-defined way; the second stream is to learn a metric from training data to ensure strong inter-class differences and intra-class similarities. However, seeking an optimal combination of visual features which is generic yet adaptive to different benchmarks is a unsoved problem, and metric learning models easily get over-fitted due to the scarcity of training data in person re-identification. In this paper, we propose two effective structured learning based approaches which explore the adaptive effects of visual features in recognizing persons in different benchmark data sets. Our framework is built on the basis of multiple low-level visual features with an optimal ensemble of their metrics. We formulate two optimization algorithms, CMCtriplet and CMCstruct, which directly optimize evaluation measures commonly used in person re-identification, also known as the Cumulative Matching Characteristic (CMC) curve.

preprint2016arXiv

The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions

One of the most intriguing features of the Visual Question Answering (VQA) challenge is the unpredictability of the questions. Extracting the information required to answer them demands a variety of image operations from detection and counting, to segmentation and reconstruction. To train a method to perform even one of these operations accurately from {image,question,answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best. We propose here instead a more general and scalable approach which exploits the fact that very good methods to achieve these operations already exist, and thus do not need to be trained. Our method thus learns how to exploit a set of external off-the-shelf algorithms to achieve its goal, an approach that has something in common with the Neural Turing Machine. The core of our proposed method is a new co-attention model. In addition, the proposed approach generates human-readable reasons for its decision, and can still be trained end-to-end without ground truth reasons being given. We demonstrate the effectiveness on two publicly available datasets, Visual Genome and VQA, and show that it produces the state-of-the-art results in both cases.

preprint2016arXiv

Visual Question Answering: A Survey of Methods and Datasets

Visual Question Answering (VQA) is a challenging task that has received increasing attention from both the computer vision and the natural language processing communities. Given an image and a question in natural language, it requires reasoning over visual elements of the image and general knowledge to infer the correct answer. In the first part of this survey, we examine the state of the art by comparing modern approaches to the problem. We classify methods by their mechanism to connect the visual and textual modalities. In particular, we examine the common approach of combining convolutional and recurrent neural networks to map images and questions to a common feature space. We also discuss memory-augmented and modular architectures that interface with structured knowledge bases. In the second part of this survey, we review the datasets available for training and evaluating VQA systems. The various datatsets contain questions at different levels of complexity, which require different capabilities and types of reasoning. We examine in depth the question/answer pairs from the Visual Genome project, and evaluate the relevance of the structured annotations of images with scene graphs for VQA. Finally, we discuss promising future directions for the field, in particular the connection to structured knowledge bases and the use of natural language processing models.

preprint2016arXiv

What value do explicit high level concepts have in vision to language problems?

Much of the recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. We propose here a method of incorporating high-level concepts into the very successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art performance in both image captioning and visual question answering. We also show that the same mechanism can be used to introduce external semantic information and that doing so further improves performance. In doing so we provide an analysis of the value of high level semantic information in V2L problems.

preprint2016arXiv

Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps

Instance retrieval requires one to search for images that contain a particular object within a large corpus. Recent studies show that using image features generated by pooling convolutional layer feature maps (CFMs) of a pretrained convolutional neural network (CNN) leads to promising performance for this task. However, due to the global pooling strategy adopted in those works, the generated image feature is less robust to image clutter and tends to be contaminated by the irrelevant image patterns. In this article, we alleviate this drawback by proposing a novel reranking algorithm using CFMs to refine the retrieval result obtained by existing methods. Our key idea, called query adaptive matching (QAM), is to first represent the CFMs of each image by a set of base regions which can be freely combined into larger regions-of-interest. Then the similarity between the query and a candidate image is measured by the best similarity score that can be attained by comparing the query feature and the feature pooled from a combined region. We show that the above procedure can be cast as an optimization problem and it can be solved efficiently with an off-the-shelf solver. Besides this general framework, we also propose two practical ways to create the base regions. One is based on the property of the CFM and the other one is based on a multi-scale spatial pyramid scheme. Through extensive experiments, we show that our reranking approaches bring substantial performance improvement and by applying them we can outperform the state of the art on several instance retrieval benchmarks.

preprint2016arXiv

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be the best way to increase performance, particularly given other limitations. Investigations into deep residual networks have also suggested that they may not in fact be operating as a single deep network, but rather as an ensemble of many relatively shallow networks. We examine these issues, and in doing so arrive at a new interpretation of the unravelled view of deep residual networks which explains some of the behaviours that have been observed experimentally. As a result, we are able to derive a new, shallower, architecture of residual networks which significantly outperforms much deeper models such as ResNet-200 on the ImageNet classification dataset. We also show that this performance is transferable to other problem domains by developing a semantic segmentation approach which outperforms the state-of-the-art by a remarkable margin on datasets including PASCAL VOC, PASCAL Context, and Cityscapes. The architecture that we propose thus outperforms its comparators, including very deep ResNets, and yet is more efficient in memory use and sometimes also in training time. The code and models are available at https://github.com/itijyou/ademxapp

preprint2015arXiv

CRF Learning with CNN Features for Image Segmentation

Conditional Random Rields (CRF) have been widely applied in image segmentations. While most studies rely on hand-crafted features, we here propose to exploit a pre-trained large convolutional neural network (CNN) to generate deep features for CRF learning. The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels. Then the CRF parameters are learnt using a structured support vector machine (SSVM). To fully exploit context information in inference, we construct spatially related co-occurrence pairwise potentials and incorporate them into the energy function. This prefers labelling of object pairs that frequently co-occur in a certain spatial layout and at the same time avoids implausible labellings during the inference. Extensive experiments on binary and multi-class segmentation benchmarks demonstrate the promise of the proposed method. We thus provide new baselines for the segmentation performance on the Weizmann horse, Graz-02, MSRC-21, Stanford Background and PASCAL VOC 2011 datasets.

preprint2015arXiv

Data Driven Robust Image Guided Depth Map Restoration

Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution. In this paper, we present a robust method for high-quality restoration of a degraded depth map with the guidance of the corresponding color image. We solve the problem in an energy optimization framework that consists of a novel robust data term and smoothness term. To accommodate not only the noise but also the inconsistency between depth discontinuities and the color edges, we model both the data term and smoothness term with a robust exponential error norm function. We propose to use Iteratively Re-weighted Least Squares (IRLS) methods for efficiently solving the resulting highly non-convex optimization problem. More importantly, we further develop a data-driven adaptive parameter selection scheme to properly determine the parameter in the model. We show that the proposed approach can preserve fine details and sharp depth discontinuities even for a large upsampling factor ($8\times$ for example). Experimental results on both simulated and real datasets demonstrate that the proposed method outperforms recent state-of-the-art methods in coping with the heavy noise, preserving sharp depth discontinuities and suppressing the texture copy artifacts.

preprint2015arXiv

Deeply Learning the Messages in Message Passing Inference

Deep structured output learning shows great promise in tasks like semantic image segmentation. We proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to estimate the messages in message passing inference for structured prediction with Conditional Random Fields (CRFs). With such CNN message estimators, we obviate the need to learn or evaluate potential functions for message calculation. This confers significant efficiency for learning, since otherwise when performing structured learning for a CRF with CNN potentials it is necessary to undertake expensive inference for every stochastic gradient iteration. The network output dimension for message estimation is the same as the number of classes, in contrast to the network output for general CNN potential functions in CRFs, which is exponential in the order of the potentials. Hence CNN message learning has fewer network parameters and is more scalable for cases that a large number of classes are involved. We apply our method to semantic image segmentation on the PASCAL VOC 2012 dataset. We achieve an intersection-over-union score of 73.4 on its test set, which is the best reported result for methods using the VOC training images alone. This impressive performance demonstrates the effectiveness and usefulness of our CNN message learning method.

preprint2015arXiv

Efficient SDP Inference for Fully-connected CRFs Based on Low-rank Decomposition

Conditional Random Fields (CRF) have been widely used in a variety of computer vision tasks. Conventional CRFs typically define edges on neighboring image pixels, resulting in a sparse graph such that efficient inference can be performed. However, these CRFs fail to model long-range contextual relationships. Fully-connected CRFs have thus been proposed. While there are efficient approximate inference methods for such CRFs, usually they are sensitive to initialization and make strong assumptions. In this work, we develop an efficient, yet general algorithm for inference on fully-connected CRFs. The algorithm is based on a scalable SDP algorithm and the low- rank approximation of the similarity/kernel matrix. The core of the proposed algorithm is a tailored quasi-Newton method that takes advantage of the low-rank matrix approximation when solving the specialized SDP dual problem. Experiments demonstrate that our method can be applied on fully-connected CRFs that cannot be solved previously, such as pixel-level image co-segmentation.

preprint2015arXiv

Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference

We propose a Branch-and-Cut (B&C) method for solving general MAP-MRF inference problems. The core of our method is a very efficient bounding procedure, which combines scalable semidefinite programming (SDP) and a cutting-plane method for seeking violated constraints. In order to further speed up the computation, several strategies have been exploited, including model reduction, warm start and removal of inactive constraints. We analyze the performance of the proposed method under different settings, and demonstrate that our method either outperforms or performs on par with state-of-the-art approaches. Especially when the connectivities are dense or when the relative magnitudes of the unary costs are low, we achieve the best reported results. Experiments show that the proposed algorithm achieves better approximation than the state-of-the-art methods within a variety of time budgets on challenging non-submodular MAP-MRF inference problems.

preprint2015arXiv

Explicit Knowledge-based Reasoning for Visual Question Answering

We describe a method for visual question answering which is capable of reasoning about contents of an image on the basis of information extracted from a large-scale knowledge base. The method not only answers natural language questions using concepts not contained in the image, but can provide an explanation of the reasoning by which it developed its answer. The method is capable of answering far more complex questions than the predominant long short-term memory-based approach, and outperforms it significantly in the testing. We also provide a dataset and a protocol by which to evaluate such methods, thus addressing one of the key issues in general visual ques- tion answering.

preprint2015arXiv

Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds

Sparsity-based representations have recently led to notable results in various visual recognition tasks. In a separate line of research, Riemannian manifolds have been shown useful for dealing with features and models that do not lie in Euclidean spaces. With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping. This in turn enables us to extend two sparse coding schemes to Grassmann manifolds. Furthermore, we propose closed-form solutions for learning a Grassmann dictionary, atom by atom. Lastly, to handle non-linearity in data, we extend the proposed Grassmann sparse coding and dictionary learning algorithms through embedding into Hilbert spaces. Experiments on several classification tasks (gender recognition, gesture classification, scene analysis, face recognition, action recognition and dynamic texture classification) show that the proposed approaches achieve considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelized Affine Hull Method and graph-embedding Grassmann discriminant analysis.

preprint2015arXiv

Fast detection of multiple objects in traffic scenes with a common detection framework

Traffic scene perception (TSP) aims to real-time extract accurate on-road environment information, which in- volves three phases: detection of objects of interest, recognition of detected objects, and tracking of objects in motion. Since recognition and tracking often rely on the results from detection, the ability to detect objects of interest effectively plays a crucial role in TSP. In this paper, we focus on three important classes of objects: traffic signs, cars, and cyclists. We propose to detect all the three important objects in a single learning based detection framework. The proposed framework consists of a dense feature extractor and detectors of three important classes. Once the dense features have been extracted, these features are shared with all detectors. The advantage of using one common framework is that the detection speed is much faster, since all dense features need only to be evaluated once in the testing phase. In contrast, most previous works have designed specific detectors using different features for each of these objects. To enhance the feature robustness to noises and image deformations, we introduce spatially pooled features as a part of aggregated channel features. In order to further improve the generalization performance, we propose an object subcategorization method as a means of capturing intra-class variation of objects. We experimentally demonstrate the effectiveness and efficiency of the proposed framework in three detection applications: traffic sign detection, car detection, and cyclist detection. The proposed framework achieves the competitive performance with state-of- the-art approaches on several benchmark datasets.

preprint2015arXiv

Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields

In this article, we tackle the problem of depth estimation from single monocular images. Compared with depth estimation using multiple images such as stereo depth perception, depth from monocular images is much more challenging. Prior work typically focuses on exploiting geometric priors or additional sources of information, most using hand-crafted features. Recently, there is mounting evidence that features from deep convolutional neural networks (CNN) set new records for various vision applications. On the other hand, considering the continuous characteristic of the depth values, depth estimations can be naturally formulated as a continuous conditional random field (CRF) learning problem. Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF. In particular, we propose a deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework. We then further propose an equally effective model based on fully convolutional networks and a novel superpixel pooling method, which is $\sim 10$ times faster, to speedup the patch-wise convolutions in the deep model. With this more efficient model, we are able to design deeper networks to pursue better performance. Experiments on both indoor and outdoor scene datasets demonstrate that the proposed method outperforms state-of-the-art depth estimation approaches.

preprint2015arXiv

Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition

The introduction of low-cost RGB-D sensors has promoted the research in skeleton-based human action recognition. Devising a representation suitable for characterising actions on the basis of noisy skeleton sequences remains a challenge, however. We here provide two insights into this challenge. First, we show that the discriminative information of a skeleton sequence usually resides in a short temporal interval and we propose a simple-but-effective local descriptor called trajectorylet to capture the static and kinematic information within this interval. Second, we further propose to encode each trajectorylet with a discriminative trajectorylet detector set which is selected from a large number of candidate detectors trained through exemplar-SVMs. The action-level representation is obtained by pooling trajectorylet encodings. Evaluating on standard datasets acquired from the Kinect sensor, it is demonstrated that our method obtains superior results over existing approaches under various experimental setups.

preprint2015arXiv

Learning to rank in person re-identification with metric ensembles

We propose an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets evaluated. Our framework is built on the basis of multiple low-level hand-crafted and high-level visual features. We then formulate two optimization algorithms, which directly optimize evaluation measures commonly used in person re-identification, also known as the Cumulative Matching Characteristic (CMC) curve. Our new approach is practical to many real-world surveillance applications as the re-identification performance can be concentrated in the range of most practical importance. The combination of these factors leads to a person re-identification system which outperforms most existing algorithms. More importantly, we advance state-of-the-art results on person re-identification by improving the rank-$1$ recognition rates from $40\%$ to $50\%$ on the iLIDS benchmark, $16\%$ to $18\%$ on the PRID2011 benchmark, $43\%$ to $46\%$ on the VIPeR benchmark, $34\%$ to $53\%$ on the CUHK01 benchmark and $21\%$ to $62\%$ on the CUHK03 benchmark.

preprint2015arXiv

Mid-level Deep Pattern Mining

Mid-level visual element discovery aims to find clusters of image patches that are both representative and discriminative. In this work, we study this problem from the prospective of pattern mining while relying on the recently popularized Convolutional Neural Networks (CNNs). Specifically, we find that for an image patch, activations extracted from the first fully-connected layer of CNNs have two appealing properties which enable its seamless integration with pattern mining. Patterns are then discovered from a large number of CNN activations of image patches through the well-known association rule mining. When we retrieve and visualize image patches with the same pattern, surprisingly, they are not only visually similar but also semantically consistent. We apply our approach to scene and object classification tasks, and demonstrate that our approach outperforms all previous works on mid-level visual element discovery by a sizeable margin with far fewer elements being used. Our approach also outperforms or matches recent works using CNN for these tasks. Source code of the complete system is available online.

preprint2015arXiv

Online Metric-Weighted Linear Representations for Robust Visual Tracking

In this paper, we propose a visual tracker based on a metric-weighted linear representation of appearance. In order to capture the interdependence of different feature dimensions, we develop two online distance metric learning methods using proximity comparison information and structured output learning. The learned metric is then incorporated into a linear representation of appearance. We show that online distance metric learning significantly improves the robustness of the tracker, especially on those sequences exhibiting drastic appearance changes. In order to bound growth in the number of training samples, we design a time-weighted reservoir sampling method. Moreover, we enable our tracker to automatically perform object identification during the process of object tracking, by introducing a collection of static template samples belonging to several object classes of interest. Object identification results for an entire video sequence are achieved by systematically combining the tracking information and visual recognition at each frame. Experimental results on challenging video sequences demonstrate the effectiveness of the method for both inter-frame tracking and object identification.

preprint2015arXiv

Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning

Many typical applications of object detection operate within a prescribed false-positive range. In this situation the performance of a detector should be assessed on the basis of the area under the ROC curve over that range, rather than over the full curve, as the performance outside the range is irrelevant. This measure is labelled as the partial area under the ROC curve (pAUC). We propose a novel ensemble learning method which achieves a maximal detection rate at a user-defined range of false positive rates by directly optimizing the partial AUC using structured learning. In order to achieve a high object detection performance, we propose a new approach to extract low-level visual features based on spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. Experimental results on both synthetic and real-world data sets demonstrate the effectiveness of our approach, and we show that it is possible to train state-of-the-art pedestrian detectors using the proposed structured ensemble learning method with spatially pooled features. The result is the current best reported performance on the Caltech-USA pedestrian detection dataset.

preprint2015arXiv

Supervised Discrete Hashing

This paper has been withdrawn by the authour.

preprint2015arXiv

Supervised Hashing Using Graph Cuts and Boosted Decision Trees

Embedding image features into a binary Hamming space can improve both the speed and accuracy of large-scale query-by-example image retrieval systems. Supervised hashing aims to map the original features to compact binary codes in a manner which preserves the label-based similarities of the original data. Most existing approaches apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of those methods, and can result in complex optimization problems that are difficult to solve. In this work we proffer a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions. The proposed framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods. Our framework decomposes the into two steps: binary code (hash bits) learning, and hash function learning. The first step can typically be formulated as a binary quadratic problem, and the second step can be accomplished by training standard binary classifiers. For solving large-scale binary code inference, we show how to ensure that the binary quadratic problems are submodular such that an efficient graph cut approach can be used. To achieve efficiency as well as efficacy on large-scale high-dimensional data, we propose to use boosted decision trees as the hash functions, which are nonlinear, highly descriptive, and very fast to train and evaluate. Experiments demonstrate that our proposed method significantly outperforms most state-of-the-art methods, especially on high-dimensional data.

preprint2015arXiv

Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition

Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of frames which is incompatible to the standard input format of CNNs. Existing methods handle this issue either by directly sampling a fixed number of frames or bypassing this issue by introducing a 3D convolutional layer which conducts convolution in spatial-temporal domain. To solve this issue, here we propose a novel network structure which allows an arbitrary number of frames as the network input. The key of our solution is to introduce a module consisting of an encoding layer and a temporal pyramid pooling layer. The encoding layer maps the activation from previous layers to a feature vector suitable for pooling while the temporal pyramid pooling layer converts multiple frame-level activations into a fixed-length video-level representation. In addition, we adopt a feature concatenation layer which combines appearance information and motion information. Compared with the frame sampling strategy, our method avoids the risk of missing any important frames. Compared with the 3D convolutional method which requires a huge video dataset for network training, our model can be learned on a small target dataset because we can leverage the off-the-shelf image-level CNN for model parameter initialization. Experiments on two challenging datasets, Hollywood2 and HMDB51, demonstrate that our method achieves superior performance over state-of-the-art methods while requiring much fewer training data.

preprint2015arXiv

Unsupervised Feature Learning for Dense Correspondences across Scenes

We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes. It is a challenging problem to estimate dense pixel correspondences between images depicting different scenes or instances of the same object category. While most such matching methods rely on hand-crafted features such as SIFT, we learn features from a large amount of unlabeled image patches using unsupervised learning. Pixel-layer features are obtained by encoding over the dictionary, followed by spatial pooling to obtain patch-layer features. The learned features are then seamlessly embedded into a multi-layer match- ing framework. We experimentally demonstrate that the learned features, together with our matching model, outperforms state-of-the-art methods such as the SIFT flow, coherency sensitive hashing and the recent deformable spatial pyramid matching methods both in terms of accuracy and computation efficiency. Furthermore, we evaluate the performance of a few different dictionary learning and feature encoding methods in the proposed pixel correspondences estimation framework, and analyse the impact of dictionary learning and feature encoding with respect to the final matching performance.

preprint2014arXiv

A Computational Model of the Short-Cut Rule for 2D Shape Decomposition

We propose a new 2D shape decomposition method based on the short-cut rule. The short-cut rule originates from cognition research, and states that the human visual system prefers to partition an object into parts using the shortest possible cuts. We propose and implement a computational model for the short-cut rule and apply it to the problem of shape decomposition. The model we proposed generates a set of cut hypotheses passing through the points on the silhouette which represent the negative minima of curvature. We then show that most part-cut hypotheses can be eliminated by analysis of local properties of each. Finally, the remaining hypotheses are evaluated in ascending length order, which guarantees that of any pair of conflicting cuts only the shortest will be accepted. We demonstrate that, compared with state-of-the-art shape decomposition methods, the proposed approach achieves decomposition results which better correspond to human intuition as revealed in psychological experiments.

preprint2014arXiv

A Generalized Probabilistic Framework for Compact Codebook Creation

Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a number of works have taken the approach of hierarchically merging visual words of an initial large-sized codebook, but implemented this approach with different merging criteria. In this work, we propose a single probabilistic framework to unify these merging criteria, by identifying two key factors: the function used to model class-conditional distribution and the method used to estimate the distribution parameters. More importantly, by adopting new distribution functions and/or parameter estimation methods, our framework can readily produce a spectrum of novel merging criteria. Three of them are specifically focused in this work. In the first criterion, we adopt the multinomial distribution with Bayesian method; In the second criterion, we integrate Gaussian distribution with maximum likelihood parameter estimation. In the third criterion, which shows the best merging performance, we propose a max-margin-based parameter estimation method and apply it with multinomial distribution. Extensive experimental study is conducted to systematically analyse the performance of the above three criteria and compare them with existing ones. As demonstrated, the best criterion obtained in our framework achieves the overall best merging performance among the comparable merging criteria developed in the literature.

preprint2014arXiv

Asymmetric Pruning for Learning Cascade Detectors

Cascade classifiers are one of the most important contributions to real-time object detection. Nonetheless, there are many challenging problems arising in training cascade detectors. One common issue is that the node classifier is trained with a symmetric classifier. Having a low misclassification error rate does not guarantee an optimal node learning goal in cascade classifiers, i.e., an extremely high detection rate with a moderate false positive rate. In this work, we present a new approach to train an effective node classifier in a cascade detector. The algorithm is based on two key observations: 1) Redundant weak classifiers can be safely discarded; 2) The final detector should satisfy the asymmetric learning objective of the cascade architecture. To achieve this, we separate the classifier training into two steps: finding a pool of discriminative weak classifiers/features and training the final classifier by pruning weak classifiers which contribute little to the asymmetric learning criterion (asymmetric classifier construction). Our model reduction approach helps accelerate the learning time while achieving the pre-determined learning objective. Experimental results on both face and car data sets verify the effectiveness of the proposed algorithm. On the FDDB face data sets, our approach achieves the state-of-the-art performance, which demonstrates the advantage of our approach.

preprint2014arXiv

Constraint Reduction using Marginal Polytope Diagrams for MAP LP Relaxations

LP relaxation-based message passing algorithms provide an effective tool for MAP inference over Probabilistic Graphical Models. However, different LP relaxations often have different objective functions and variables of differing dimensions, which presents a barrier to effective comparison and analysis. In addition, the computational complexity of LP relaxation-based methods grows quickly with the number of constraints. Reducing the number of constraints without sacrificing the quality of the solutions is thus desirable. We propose a unified formulation under which existing MAP LP relaxations may be compared and analysed. Furthermore, we propose a new tool called Marginal Polytope Diagrams. Some properties of Marginal Polytope Diagrams are exploited such as node redundancy and edge equivalence. We show that using Marginal Polytope Diagrams allows the number of constraints to be reduced without loosening the LP relaxations. Then, using Marginal Polytope Diagrams and constraint reduction, we develop three novel message passing algorithms, and demonstrate that two of these show a significant improvement in speed over state-of-art algorithms while delivering a competitive, and sometimes higher, quality of solution.

preprint2014arXiv

Context-Aware Hypergraph Construction for Robust Spectral Clustering

Spectral clustering is a powerful tool for unsupervised data analysis. In this paper, we propose a context-aware hypergraph similarity measure (CAHSM), which leads to robust spectral clustering in the case of noisy data. We construct three types of hypergraph---the pairwise hypergraph, the k-nearest-neighbor (kNN) hypergraph, and the high-order over-clustering hypergraph. The pairwise hypergraph captures the pairwise similarity of data points; the kNN hypergraph captures the neighborhood of each point; and the clustering hypergraph encodes high-order contexts within the dataset. By combining the affinity information from these three hypergraphs, the CAHSM algorithm is able to explore the intrinsic topological information of the dataset. Therefore, data clustering using CAHSM tends to be more robust. Considering the intra-cluster compactness and the inter-cluster separability of vertices, we further design a discriminative hypergraph partitioning criterion (DHPC). Using both CAHSM and DHPC, a robust spectral clustering algorithm is developed. Theoretical analysis and experimental evaluation demonstrate the effectiveness and robustness of the proposed algorithm.

preprint2014arXiv

Deep Convolutional Neural Fields for Depth Estimation from a Single Image

We consider the problem of depth estimation from a single monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo correspondences, motions, etc. Previous efforts have been focusing on exploiting geometric priors or additional sources of information, with all using hand-crafted features. Recently, there is mounting evidence that features from deep convolutional neural networks (CNN) are setting new records for various vision applications. On the other hand, considering the continuous characteristic of the depth values, depth estimations can be naturally formulated into a continuous conditional random field (CRF) learning problem. Therefore, we in this paper present a deep convolutional neural field model for estimating depths from a single image, aiming to jointly explore the capacity of deep CNN and continuous CRF. Specifically, we propose a deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework. The proposed method can be used for depth estimations of general scenes with no geometric priors nor any extra information injected. In our case, the integral of the partition function can be analytically calculated, thus we can exactly solve the log-likelihood optimization. Moreover, solving the MAP problem for predicting depths of a new image is highly efficient as closed-form solutions exist. We experimentally demonstrate that the proposed method outperforms state-of-the-art depth estimation methods on both indoor and outdoor scene datasets.

preprint2014arXiv

Efficient Semidefinite Spectral Clustering via Lagrange Duality

We propose an efficient approach to semidefinite spectral clustering (SSC), which addresses the Frobenius normalization with the positive semidefinite (p.s.d.) constraint for spectral clustering. Compared with the original Frobenius norm approximation based algorithm, the proposed algorithm can more accurately find the closest doubly stochastic approximation to the affinity matrix by considering the p.s.d. constraint. In this paper, SSC is formulated as a semidefinite programming (SDP) problem. In order to solve the high computational complexity of SDP, we present a dual algorithm based on the Lagrange dual formalization. Two versions of the proposed algorithm are proffered: one with less memory usage and the other with faster convergence rate. The proposed algorithm has much lower time complexity than that of the standard interior-point based SDP solvers. Experimental results on both UCI data sets and real-world image data sets demonstrate that 1) compared with the state-of-the-art spectral clustering methods, the proposed algorithm achieves better clustering performance; and 2) our algorithm is much more efficient and can solve larger-scale SSC problems than those standard interior-point SDP solvers.

preprint2014arXiv

Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors

Deriving from the gradient vector of a generative model of local features, Fisher vector coding (FVC) has been identified as an effective coding method for image classification. Most, if not all, % FVC implementations employ the Gaussian mixture model (GMM) to characterize the generation process of local features. This choice has shown to be sufficient for traditional low dimensional local features, e.g., SIFT; and typically, good performance can be achieved with only a few hundred Gaussian distributions. However, the same number of Gaussians is insufficient to model the feature space spanned by higher dimensional local features, which have become popular recently. In order to improve the modeling capacity for high dimensional features, it turns out to be inefficient and computationally impractical to simply increase the number of Gaussians. In this paper, we propose a model in which each local feature is drawn from a Gaussian distribution whose mean vector is sampled from a subspace. With certain approximation, this model can be converted to a sparse coding procedure and the learning/inference problems can be readily solved by standard sparse coding methods. By calculating the gradient vector of the proposed model, we derive a new fisher vector encoding strategy, termed Sparse Coding based Fisher Vector Coding (SCFVC). Moreover, we adopt the recently developed Deep Convolutional Neural Network (CNN) descriptor as a high dimensional local feature and implement image classification with the proposed SCFVC. Our experimental evaluations demonstrate that our method not only significantly outperforms the traditional GMM based Fisher vector encoding but also achieves the state-of-the-art performance in generic object recognition, indoor scene, and fine-grained image classification problems.

preprint2014arXiv

Face Identification with Second-Order Pooling

Automatic face recognition has received significant performance improvement by developing specialised facial image representations. On the other hand, generic object recognition has rarely been applied to the face recognition. Spatial pyramid pooling of features encoded by an over-complete dictionary has been the key component of many state-of-the-art image classification systems. Inspired by its success, in this work we develop a new face image representation method inspired by the second-order pooling in Carreira et al. [1], which was originally proposed for image segmentation. The proposed method differs from the previous methods in that, we encode the densely extracted local patches by a small-size dictionary; and the facial image signatures are obtained by pooling the second-order statistics of the encoded features. We show the importance of pooling on encoded features, which is bypassed by the original second-order pooling method to avoid the high computational cost. Equipped with a simple linear classifier, the proposed method outperforms the state-of-the-art face identification performance by large margins. For example, on the LFW databases, the proposed method performs better than the previous best by around 13% accuracy.

preprint2014arXiv

Face Image Classification by Pooling Raw Features

We propose a very simple, efficient yet surprisingly effective feature extraction method for face recognition (about 20 lines of Matlab code), which is mainly inspired by spatial pyramid pooling in generic image classification. We show that features formed by simply pooling local patches over a multi-level pyramid, coupled with a linear classifier, can significantly outperform most recent face recognition methods. The simplicity of our feature extraction procedure is demonstrated by the fact that no learning is involved (except PCA whitening). We show that, multi-level spatial pooling and dense extraction of multi-scale patches play critical roles in face image classification. The extracted facial features can capture strong structural information of individual faces with no label information being used. We also find that, pre-processing on local image patches such as contrast normalization can have an important impact on the classification accuracy. In particular, on the challenging face recognition datasets of FERET and LFW-a, our method improves previous best results by more than 10% and 20%, respectively.

preprint2014arXiv

Fast Supervised Hashing with Decision Trees for High-Dimensional Data

Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear hash functions have demonstrated the advantage over linear ones due to their powerful generalization capability. In the literature, kernel functions are typically used to achieve non-linearity in hashing, which achieve encouraging retrieval performance at the price of slow evaluation and training time. Here we propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data. In our approach, we first propose sub-modular formulations for the hashing binary code inference problem and an efficient GraphCut based block search method for solving large-scale inference. Then we learn hash functions by training boosted decision trees to fit the binary codes. Experiments demonstrate that our proposed method significantly outperforms most state-of-the-art methods in retrieval precision and training time. Especially for high-dimensional data, our method is orders of magnitude faster than many methods in terms of training time.

preprint2014arXiv

From Kernel Machines to Ensemble Learning

Ensemble methods such as boosting combine multiple learners to obtain better prediction than could be obtained from any individual learner. Here we propose a principled framework for directly constructing ensemble learning methods from kernel methods. Unlike previous studies showing the equivalence between boosting and support vector machines (SVMs), which needs a translation procedure, we show that it is possible to design boosting-like procedure to solve the SVM optimization problems. In other words, it is possible to design ensemble methods directly from SVM without any middle procedure. This finding not only enables us to design new ensemble learning methods directly from kernel methods, but also makes it possible to take advantage of those highly-optimized fast linear SVM solvers for ensemble learning. We exemplify this framework for designing binary ensemble learning as well as a new multi-class ensemble learning methods. Experimental results demonstrate the flexibility and usefulness of the proposed framework.

preprint2014arXiv

Hashing on Nonlinear Manifolds

Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes preserving the Euclidean similarity in the original space. Manifold learning techniques, in contrast, are better able to model the intrinsic structure embedded in the original high-dimensional data. The complexities of these models, and the problems with out-of-sample data, have previously rendered them unsuitable for application to large-scale embedding, however. In this work, how to learn compact binary embeddings on their intrinsic manifolds is considered. In order to address the above-mentioned difficulties, an efficient, inductive solution to the out-of-sample data problem, and a process by which non-parametric manifold learning may be used as the basis of a hashing method is proposed. The proposed approach thus allows the development of a range of new hashing techniques exploiting the flexibility of the wide variety of manifold learning approaches available. It is particularly shown that hashing on the basis of t-SNE outperforms state-of-the-art hashing methods on large-scale benchmark datasets, and is very effective for image classification with very short code lengths. The proposed hashing framework is shown to be easily improved, for example, by minimizing the quantization error with learned orthogonal rotations. In addition, a supervised inductive manifold hashing framework is developed by incorporating the label information, which is shown to greatly advance the semantic retrieval performance.

preprint2014arXiv

Large-margin Learning of Compact Binary Image Encodings

The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed, however. We address this problem by developing a novel approach to learning a compact binary encoding, which exploits both pair-wise proximity and class-label information on training data set. Exploiting this extra information allows the development of encodings which, although compact, outperform the original high-dimensional features in terms of final classification or retrieval performance. The method is general, in that it is applicable to both non-parametric and parametric learning methods. This generality means that the embedded features are suitable for a wide variety of computer vision tasks, such as image classification and content-based image retrieval. Experimental results demonstrate that the new compact descriptor achieves an accuracy comparable to, and in some cases better than, the visual descriptor in the original space despite being significantly more compact. Moreover, any convex loss function and convex regularization penalty (e.g., $ \ell_p $ norm with $ p \ge 1 $) can be incorporated into the framework, which provides future flexibility.

preprint2014arXiv

Learning Deep Convolutional Features for MRI Based Alzheimer's Disease Classification

Effective and accurate diagnosis of Alzheimer's disease (AD) or mild cognitive impairment (MCI) can be critical for early treatment and thus has attracted more and more attention nowadays. Since first introduced, machine learning methods have been gaining increasing popularity for AD related research. Among the various identified biomarkers, magnetic resonance imaging (MRI) are widely used for the prediction of AD or MCI. However, before a machine learning algorithm can be applied, image features need to be extracted to represent the MRI images. While good representations can be pivotal to the classification performance, almost all the previous studies typically rely on human labelling to find the regions of interest (ROI) which may be correlated to AD, such as hippocampus, amygdala, precuneus, etc. This procedure requires domain knowledge and is costly and tedious. Instead of relying on extraction of ROI features, it is more promising to remove manual ROI labelling from the pipeline and directly work on the raw MRI images. In other words, we can let the machine learning methods to figure out these informative and discriminative image structures for AD classification. In this work, we propose to learn deep convolutional image features using unsupervised and supervised learning. Deep learning has emerged as a powerful tool in the machine learning community and has been successfully applied to various tasks. We thus propose to exploit deep features of MRI images based on a pre-trained large convolutional neural network (CNN) for AD and MCI classification, which spares the effort of manual ROI annotation process.

preprint2014arXiv

Optimizing Ranking Measures for Compact Binary Code Learning

Hashing has proven a valuable tool for large-scale information retrieval. Despite much success, existing hashing methods optimize over simple objectives such as the reconstruction error or graph Laplacian related loss functions, instead of the performance evaluation criteria of interest---multivariate performance measures such as the AUC and NDCG. Here we present a general framework (termed StructHash) that allows one to directly optimize multivariate performance measures. The resulting optimization problem can involve exponentially or infinitely many variables and constraints, which is more challenging than standard structured output learning. To solve the StructHash optimization problem, we use a combination of column generation and cutting-plane techniques. We demonstrate the generality of StructHash by applying it to ranking prediction and image retrieval, and show that it outperforms a few state-of-the-art hashing methods.

preprint2014arXiv

Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features

We propose a simple yet effective approach to the problem of pedestrian detection which outperforms the current state-of-the-art. Our new features are built on the basis of low-level visual features and spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. We then directly optimise the partial area under the ROC curve (\pAUC) measure, which concentrates detection performance in the range of most practical importance. The combination of these factors leads to a pedestrian detector which outperforms all competitors on all of the standard benchmark datasets. We advance state-of-the-art results by lowering the average miss rate from $13\%$ to $11\%$ on the INRIA benchmark, $41\%$ to $37\%$ on the ETH benchmark, $51\%$ to $42\%$ on the TUD-Brussels benchmark and $36\%$ to $29\%$ on the Caltech-USA benchmark.

preprint2014arXiv

The Treasure beneath Convolutional Layers: Cross-convolutional-layer Pooling for Image Classification

A number of recent studies have shown that a Deep Convolutional Neural Network (DCNN) pretrained on a large dataset can be adopted as a universal image description which leads to astounding performance in many visual classification tasks. Most of these studies, if not all, adopt activations of the fully-connected layer of a DCNN as the image or region representation and it is believed that convolutional layer activations are less discriminative. This paper, however, advocates that if used appropriately convolutional layer activations can be turned into a powerful image representation which enjoys many advantages over fully-connected layer activations. This is achieved by adopting a new technique proposed in this paper called cross-convolutional-layer pooling. More specifically, it extracts subarrays of feature maps of one convolutional layer as local features and pools the extracted features with the guidance of feature maps of the successive convolutional layer. Compared with exising methods that apply DCNNs in the local feature setting, the proposed method is significantly faster since it requires much fewer times of DCNN forward computation. Moreover, it avoids the domain mismatch issue which is usually encountered when applying fully connected layer activations to describe local regions. By applying our method to four popular visual classification tasks, it is demonstrated that the proposed method can achieve comparable or in some cases significantly better performance than existing fully-connected layer based image representations while incurring much lower computational cost.

preprint2013arXiv

A Fast Semidefinite Approach to Solving Binary Quadratic Problems

Many computer vision problems can be formulated as binary quadratic programs (BQPs). Two classic relaxation methods are widely used for solving BQPs, namely, spectral methods and semidefinite programming (SDP), each with their own advantages and disadvantages. Spectral relaxation is simple and easy to implement, but its bound is loose. Semidefinite relaxation has a tighter bound, but its computational complexity is high for large scale problems. We present a new SDP formulation for BQPs, with two desirable properties. First, it has a similar relaxation bound to conventional SDP formulations. Second, compared with conventional SDP methods, the new SDP formulation leads to a significantly more efficient and scalable dual optimization approach, which has the same degree of complexity as spectral methods. Extensive experiments on various applications including clustering, image segmentation, co-segmentation and registration demonstrate the usefulness of our SDP formulation for solving large-scale BQPs.

preprint2013arXiv

A General Two-Step Approach to Learning-Based Hashing

Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of the method to respond to the data, and can result in complex optimization problems that are difficult to solve. Here we propose a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions. This framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods. Our framework decomposes hashing learning problem into two steps: hash bit learning and hash function learning based on the learned bits. The first step can typically be formulated as binary quadratic problems, and the second step can be accomplished by training standard binary classifiers. Both problems have been extensively studied in the literature. Our extensive experiments demonstrate that the proposed framework is effective, flexible and outperforms the state-of-the-art.

preprint2013arXiv

A scalable stage-wise approach to large-margin multi-class loss based boosting

We present a scalable and effective classification model to train multi-class boosting for multi-class classification problems. Shen and Hao introduced a direct formulation of multi- class boosting in the sense that it directly maximizes the multi- class margin [C. Shen and Z. Hao, "A direct formulation for totally-corrective multi- class boosting", in Proc. IEEE Conf. Comp. Vis. Patt. Recogn., 2011]. The major problem of their approach is its high computational complexity for training, which hampers its application on real-world problems. In this work, we propose a scalable and simple stage-wise multi-class boosting method, which also directly maximizes the multi-class margin. Our approach of- fers a few advantages: 1) it is simple and computationally efficient to train. The approach can speed up the training time by more than two orders of magnitude without sacrificing the classification accuracy. 2) Like traditional AdaBoost, it is less sensitive to the choice of parameters and empirically demonstrates excellent generalization performance. Experimental results on challenging multi-class machine learning and vision tasks demonstrate that the proposed approach substantially improves the convergence rate and accuracy of the final visual detector at no additional computational cost compared to existing multi-class boosting.

preprint2013arXiv

A Survey of Appearance Models in Visual Object Tracking

Visual object tracking is a significant computer vision task which can be applied to many domains such as visual surveillance, human computer interaction, and video compression. In the literature, researchers have proposed a variety of 2D appearance models. To help readers swiftly learn the recent advances in 2D appearance models for visual object tracking, we contribute this survey, which provides a detailed review of the existing 2D appearance models. In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking. In this survey, we first decompose the problem of appearance modeling into two different processing stages: visual representation and statistical modeling. Then, different 2D appearance models are categorized and discussed with respect to their composition modules. Finally, we address several issues of interest as well as the remaining challenges for future research on this topic. The contributions of this survey are four-fold. First, we review the literature of visual representations according to their feature-construction mechanisms (i.e., local and global). Second, the existing statistical modeling schemes for tracking-by-detection are reviewed according to their model-construction mechanisms: generative, discriminative, and hybrid generative-discriminative. Third, each type of visual representations or statistical modeling techniques is analyzed and discussed from a theoretical or practical viewpoint. Fourth, the existing benchmark resources (e.g., source code and video datasets) are examined in this survey.

preprint2013arXiv

An Efficient Dual Approach to Distance Metric Learning

Distance metric learning is of fundamental interest in machine learning because the distance metric employed can significantly affect the performance of many learning methods. Quadratic Mahalanobis metric learning is a popular approach to the problem, but typically requires solving a semidefinite programming (SDP) problem, which is computationally expensive. Standard interior-point SDP solvers typically have a complexity of $O(D^{6.5})$ (with $D$ the dimension of input data), and can thus only practically solve problems exhibiting less than a few thousand variables. Since the number of variables is $D (D+1) / 2 $, this implies a limit upon the size of problem that can practically be solved of around a few hundred dimensions. The complexity of the popular quadratic Mahalanobis metric learning approach thus limits the size of problem to which metric learning can be applied. Here we propose a significantly more efficient approach to the metric learning problem based on the Lagrange dual formulation of the problem. The proposed formulation is much simpler to implement, and therefore allows much larger Mahalanobis metric learning problems to be solved. The time complexity of the proposed method is $O (D ^ 3) $, which is significantly lower than that of the SDP approach. Experiments on a variety of datasets demonstrate that the proposed method achieves an accuracy comparable to the state-of-the-art, but is applicable to significantly larger problems. We also show that the proposed method can be applied to solve more general Frobenius-norm regularized SDP problems approximately.

preprint2013arXiv

Characterness: An Indicator of Text in the Wild

Text in an image provides vital information for interpreting its contents, and text in a scene can aide with a variety of tasks from navigation, to obstacle avoidance, and odometry. Despite its value, however, identifying general text in images remains a challenging research problem. Motivated by the need to consider the widely varying forms of natural text, we propose a bottom-up approach to the problem which reflects the `characterness' of an image region. In this sense our approach mirrors the move from saliency detection methods to measures of `objectness'. In order to measure the characterness we develop three novel cues that are tailored for character detection, and a Bayesian method for their integration. Because text is made up of sets of characters, we then design a Markov random field (MRF) model so as to exploit the inherent dependencies between characters. We experimentally demonstrate the effectiveness of our characterness cues as well as the advantage of Bayesian multi-cue integration. The proposed text detector outperforms state-of-the-art methods on a few benchmark scene text detection datasets. We also show that our measurement of `characterness' is superior than state-of-the-art saliency detection models when applied to the same task.

preprint2013arXiv

Contextual Hypergraph Modelling for Salient Object Detection

Salient object detection aims to locate objects that capture human attention within images. Previous approaches often pose this as a problem of image contrast analysis. In this work, we model an image as a hypergraph that utilizes a set of hyperedges to capture the contextual properties of image pixels or regions. As a result, the problem of salient object detection becomes one of finding salient vertices and hyperedges in the hypergraph. The main advantage of hypergraph modeling is that it takes into account each pixel's (or region's) affinity with its neighborhood as well as its separation from image background. Furthermore, we propose an alternative approach based on center-versus-surround contextual contrast analysis, which performs salient object detection by optimizing a cost-sensitive support vector machine (SVM) objective function. Experimental results on four challenging datasets demonstrate the effectiveness of the proposed approaches against the state-of-the-art approaches to salient object detection.

preprint2013arXiv

Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables us to devise a closed-form solution for updating a Grassmann dictionary, atom by atom. Furthermore, to handle non-linearity in data, we propose a kernelised version of the dictionary learning algorithm. Experiments on several classification tasks (face recognition, action recognition, dynamic texture classification) show that the proposed approach achieves considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelised Affine Hull Method and graph-embedding Grassmann discriminant analysis.

preprint2013arXiv

Efficient pedestrian detection by directly optimize the partial area under the ROC curve

Many typical applications of object detection operate within a prescribed false-positive range. In this situation the performance of a detector should be assessed on the basis of the area under the ROC curve over that range, rather than over the full curve, as the performance outside the range is irrelevant. This measure is labelled as the partial area under the ROC curve (pAUC). Effective cascade-based classification, for example, depends on training node classifiers that achieve the maximal detection rate at a moderate false positive rate, e.g., around 40% to 50%. We propose a novel ensemble learning method which achieves a maximal detection rate at a user-defined range of false positive rates by directly optimizing the partial AUC using structured learning. By optimizing for different ranges of false positive rates, the proposed method can be used to train either a single strong classifier or a node classifier forming part of a cascade classifier. Experimental results on both synthetic and real-world data sets demonstrate the effectiveness of our approach, and we show that it is possible to train state-of-the-art pedestrian detectors using the proposed structured ensemble learning method.

preprint2013arXiv

Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization

Wepresentanovelcolumngenerationbasedboostingmethod for multi-class classification. Our multi-class boosting is formulated in a single optimization problem as in Shen and Hao (2011). Different from most existing multi-class boosting methods, which use the same set of weak learners for all the classes, we train class specified weak learners (i.e., each class has a different set of weak learners). We show that using separate weak learner sets for each class leads to fast convergence, without introducing additional computational overhead in the training procedure. To further make the training more efficient and scalable, we also propose a fast co- ordinate descent method for solving the optimization problem at each boosting iteration. The proposed coordinate descent method is conceptually simple and easy to implement in that it is a closed-form solution for each coordinate update. Experimental results on a variety of datasets show that, compared to a range of existing multi-class boosting meth- ods, the proposed method has much faster convergence rate and better generalization performance in most cases. We also empirically show that the proposed fast coordinate descent algorithm needs less training time than the MultiBoost algorithm in Shen and Hao (2011).

preprint2013arXiv

Generic Image Classification Approaches Excel on Face Recognition

The main finding of this work is that the standard image classification pipeline, which consists of dictionary learning, feature encoding, spatial pyramid pooling and linear classification, outperforms all state-of-the-art face recognition methods on the tested benchmark datasets (we have tested on AR, Extended Yale B, the challenging FERET, and LFW-a datasets). This surprising and prominent result suggests that those advances in generic image classification can be directly applied to improve face recognition systems. In other words, face recognition may not need to be viewed as a separate object classification problem. While recently a large body of residual based face recognition methods focus on developing complex dictionary learning algorithms, in this work we show that a dictionary of randomly extracted patches (even from non-face images) can achieve very promising results using the image classification pipeline. That means, the choice of dictionary learning methods may not be important. Instead, we find that learning multiple dictionaries using different low-level image features often improve the final classification accuracy. Our proposed face recognition approach offers the best reported results on the widely-used face recognition benchmark datasets. In particular, on the challenging FERET and LFW-a datasets, we improve the best reported accuracies in the literature by about 20% and 30% respectively.

preprint2013arXiv

Inductive Hashing on Manifolds

preprint2013arXiv

Learning Hash Functions Using Column Generation

Fast nearest neighbor searching is becoming an increasingly important tool in solving many large-scale problems. Recently a number of approaches to learning data-dependent hash functions have been developed. In this work, we propose a column generation based method for learning data-dependent hash functions on the basis of proximity comparison information. Given a set of triplets that encode the pairwise proximity comparison information, our method learns hash functions that preserve the relative comparison relationships in the data as well as possible within the large-margin learning framework. The learning procedure is implemented using column generation and hence is named CGHash. At each iteration of the column generation procedure, the best hash function is selected. Unlike most other hashing methods, our method generalizes to new data points naturally; and has a training objective which is convex, thus ensuring that the global optimum can be identified. Experiments demonstrate that the proposed method learns compact binary codes and that its retrieval performance compares favorably with state-of-the-art methods when tested on a few benchmark datasets.

preprint2013arXiv

Multiple Kernel Learning in the Primal for Multi-modal Alzheimer's Disease Classification

To achieve effective and efficient detection of Alzheimer's disease (AD), many machine learning methods have been introduced into this realm. However, the general case of limited training samples, as well as different feature representations typically makes this problem challenging. In this work, we propose a novel multiple kernel learning framework to combine multi-modal features for AD classification, which is scalable and easy to implement. Contrary to the usual way of solving the problem in the dual space, we look at the optimization from a new perspective. By conducting Fourier transform on the Gaussian kernel, we explicitly compute the mapping function, which leads to a more straightforward solution of the problem in the primal space. Furthermore, we impose the mixed $L_{21}$ norm constraint on the kernel weights, known as the group lasso regularization, to enforce group sparsity among different feature modalities. This actually acts as a role of feature modality selection, while at the same time exploiting complementary information among different kernels. Therefore it is able to extract the most discriminative features for classification. Experiments on the ADNI data set demonstrate the effectiveness of the proposed method.

preprint2013arXiv

Online Unsupervised Feature Learning for Visual Tracking

Feature encoding with respect to an over-complete dictionary learned by unsupervised methods, followed by spatial pyramid pooling, and linear classification, has exhibited powerful strength in various vision applications. Here we propose to use the feature learning pipeline for visual tracking. Tracking is implemented using tracking-by-detection and the resulted framework is very simple yet effective. First, online dictionary learning is used to build a dictionary, which captures the appearance changes of the tracking target as well as the background changes. Given a test image window, we extract local image patches from it and each local patch is encoded with respect to the dictionary. The encoded features are then pooled over a spatial pyramid to form an aggregated feature vector. Finally, a simple linear classifier is trained on these features. Our experiments show that the proposed powerful---albeit simple---tracker, outperforms all the state-of-the-art tracking methods that we have tested. Moreover, we evaluate the performance of different dictionary learning and feature encoding methods in the proposed tracking framework, and analyse the impact of each component in the tracking scenario. We also demonstrate the flexibility of feature learning by plugging it into Hare et al.'s tracking method. The outcome is, to our knowledge, the best tracker ever reported, which facilitates the advantages of both feature learning and structured output prediction.

preprint2013arXiv

RandomBoost: Simplified Multi-class Boosting through Randomization

We propose a novel boosting approach to multi-class classification problems, in which multiple classes are distinguished by a set of random projection matrices in essence. The approach uses random projections to alleviate the proliferation of binary classifiers typically required to perform multi-class classification. The result is a multi-class classifier with a single vector-valued parameter, irrespective of the number of classes involved. Two variants of this approach are proposed. The first method randomly projects the original data into new spaces, while the second method randomly projects the outputs of learned weak classifiers. These methods are not only conceptually simple but also effective and easy to implement. A series of experiments on synthetic, machine learning and visual recognition data sets demonstrate that our proposed methods compare favorably to existing multi-class boosting algorithms in terms of both the convergence rate and classification accuracy.

preprint2013arXiv

Training Effective Node Classifiers for Cascade Classification

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are a few reported methods addressing this requirement in the context of object detection, there is no principled feature selection method that explicitly takes into account this asymmetric node learning objective. We provide such an algorithm here. We show that a special case of the biased minimax probability machine has the same formulation as the linear asymmetric classifier (LAC) of Wu et al (2005). We then design a new boosting algorithm that directly optimizes the cost function of LAC. The resulting totally-corrective boosting algorithm is implemented by the column generation technique in convex optimization. Experimental results on object detection verify the effectiveness of the proposed boosting algorithm as a node classifier in cascade object detection, and show performance better than that of the current state-of-the-art.

preprint2012arXiv

A Direct Approach to Multi-class Boosting and Extensions

Boosting methods combine a set of moderately accurate weaklearners to form a highly accurate predictor. Despite the practical importance of multi-class boosting, it has received far less attention than its binary counterpart. In this work, we propose a fully-corrective multi-class boosting formulation which directly solves the multi-class problem without dividing it into multiple binary classification problems. In contrast, most previous multi-class boosting algorithms decompose a multi-boost problem into multiple binary boosting problems. By explicitly deriving the Lagrange dual of the primal optimization problem, we are able to construct a column generation-based fully-corrective approach to boosting which directly optimizes multi-class classification performance. The new approach not only updates all weak learners' coefficients at every iteration, but does so in a manner flexible enough to accommodate various loss functions and regularizations. For example, it enables us to introduce structural sparsity through mixed-norm regularization to promote group sparsity and feature sharing. Boosting with shared features is particularly beneficial in complex prediction problems where features can be expensive to compute. Our experiments on various data sets demonstrate that our direct multi-class boosting generalizes as well as, or better than, a range of competing multi-class boosting methods. The end result is a highly effective and compact ensemble classifier which can be trained in a distributed fashion.

preprint2012arXiv

Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking

Visual tracking usually requires an object appearance model that is robust to changing illumination, pose and other factors encountered in video. In this paper, we construct an appearance model using the 3D discrete cosine transform (3D-DCT). The 3D-DCT is based on a set of cosine basis functions, which are determined by the dimensions of the 3D signal and thus independent of the input video data. In addition, the 3D-DCT can generate a compact energy spectrum whose high-frequency coefficients are sparse if the appearance samples are similar. By discarding these high-frequency coefficients, we simultaneously obtain a compact 3D-DCT based object representation and a signal reconstruction-based similarity measure (reflecting the information loss from signal reconstruction). To efficiently update the object representation, we propose an incremental 3D-DCT algorithm, which decomposes the 3D-DCT into successive operations of the 2D discrete cosine transform (2D-DCT) and 1D discrete cosine transform (1D-DCT) on the input video data.

preprint2012arXiv

Is margin preserved after random projection?

Random projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this paper we analyse margin distortion after random projection, and give the conditions of margin preservation for binary classification problems. We also extend our analysis to margin for multiclass problems, and provide theoretical bounds on multiclass margin on the projected data.

preprint2012arXiv

Non-sparse Linear Representations for Visual Tracking with Online Reservoir Metric Learning

Most sparse linear representation-based trackers need to solve a computationally expensive L1-regularized optimization problem. To address this problem, we propose a visual tracker based on non-sparse linear representations, which admit an efficient closed-form solution without sacrificing accuracy. Moreover, in order to capture the correlation information between different feature dimensions, we learn a Mahalanobis distance metric in an online fashion and incorporate the learned metric into the optimization problem for obtaining the linear representation. We show that online metric learning using proximity comparison significantly improves the robustness of the tracking, especially on those sequences exhibiting drastic appearance changes. Furthermore, in order to prevent the unbounded growth in the number of training samples for the metric learning, we design a time-weighted reservoir sampling method to maintain and update limited-sized foreground and background sample buffers for balancing sample diversity and adaptability. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.

preprint2012arXiv

Positive Semidefinite Metric Learning Using Boosting-like Algorithms

The success of many machine learning and pattern recognition methods relies heavily upon the identification of an appropriate distance metric on the input data. It is often beneficial to learn such a metric from the input training data, instead of using a default one such as the Euclidean distance. In this work, we propose a boosting-based technique, termed BoostMetric, for learning a quadratic Mahalanobis distance metric. Learning a valid Mahalanobis distance metric requires enforcing the constraint that the matrix parameter to the metric remains positive definite. Semidefinite programming is often used to enforce this constraint, but does not scale well and easy to implement. BoostMetric is instead based on the observation that any positive semidefinite matrix can be decomposed into a linear combination of trace-one rank-one matrices. BoostMetric thus uses rank-one positive semidefinite matrices as weak learners within an efficient and scalable boosting-based learning process. The resulting methods are easy to implement, efficient, and can accommodate various types of constraints. We extend traditional boosting algorithms in that its weak learner is a positive semidefinite matrix with trace and rank being one rather than a classifier or regressor. Experiments on various datasets demonstrate that the proposed algorithms compare favorably to those state-of-the-art methods in terms of classification accuracy and running time.

preprint2011arXiv

Face Recognition using Optimal Representation Ensemble

Recently, the face recognizers based on linear representations have been shown to deliver state-of-the-art performance. In real-world applications, however, face images usually suffer from expressions, disguises and random occlusions. The problematic facial parts undermine the validity of the linear-subspace assumption and thus the recognition performance deteriorates significantly. In this work, we address the problem in a learning-inference-mixed fashion. By observing that the linear-subspace assumption is more reliable on certain face patches rather than on the holistic face, some Bayesian Patch Representations (BPRs) are randomly generated and interpreted according to the Bayes' theory. We then train an ensemble model over the patch-representations by minimizing the empirical risk w.r.t the "leave-one-out margins". The obtained model is termed Optimal Representation Ensemble (ORE), since it guarantees the optimality from the perspective of Empirical Risk Minimization. To handle the unknown patterns in test faces, a robust version of BPR is proposed by taking the non-face category into consideration. Equipped with the Robust-BPRs, the inference ability of ORE is increased dramatically and several record-breaking accuracies (99.9% on Yale-B and 99.5% on AR) and desirable efficiencies (below 20 ms per face in Matlab) are achieved. It also overwhelms other modular heuristics on the faces with random occlusions, extreme expressions and disguises. Furthermore, to accommodate immense BPRs sets, a boosting-like algorithm is also derived. The boosted model, a.k.a Boosted-ORE, obtains similar performance to its prototype. Besides the empirical superiorities, two desirable features of the proposed methods, namely, the training-determined model-selection and the data-weight-free boosting procedure, are also theoretically verified.

preprint2011arXiv

Totally Corrective Boosting for Regularized Risk Minimization

Consideration of the primal and dual problems together leads to important new insights into the characteristics of boosting algorithms. In this work, we propose a general framework that can be used to design new boosting algorithms. A wide variety of machine learning problems essentially minimize a regularized risk functional. We show that the proposed boosting framework, termed CGBoost, can accommodate various loss functions and different regularizers in a totally-corrective optimization fashion. We show that, by solving the primal rather than the dual, a large body of totally-corrective boosting algorithms can actually be efficiently solved and no sophisticated convex optimization solvers are needed. We also demonstrate that some boosting algorithms like AdaBoost can be interpreted in our framework--even their optimization is not totally corrective. We empirically show that various boosting algorithms based on the proposed framework perform similarly on the UCIrvine machine learning datasets [1] that we have used in the experiments.

preprint2010arXiv

Asymmetric Totally-corrective Boosting for Real-time Object Detection

Real-time object detection is one of the core problems in computer vision. The cascade boosting framework proposed by Viola and Jones has become the standard for this problem. In this framework, the learning goal for each node is asymmetric, which is required to achieve a high detection rate and a moderate false positive rate. We develop new boosting algorithms to address this asymmetric learning problem. We show that our methods explicitly optimize asymmetric loss objectives in a totally corrective fashion. The methods are totally corrective in the sense that the coefficients of all selected weak classifiers are updated at each iteration. In contract, conventional boosting like AdaBoost is stage-wise in that only the current weak classifier's coefficient is updated. At the heart of the totally corrective boosting is the column generation technique. Experiments on face detection show that our methods outperform the state-of-the-art asymmetric boosting methods.

preprint2010arXiv

Boosting through Optimization of Margin Distributions

Boosting has attracted much research attention in the past decade. The success of boosting algorithms may be interpreted in terms of the margin theory. Recently it has been shown that generalization error of classifiers can be obtained by explicitly taking the margin distribution of the training data into account. Most of the current boosting algorithms in practice usually optimizes a convex loss function and do not make use of the margin distribution. In this work we design a new boosting algorithm, termed margin-distribution boosting (MDBoost), which directly maximizes the average margin and minimizes the margin variance simultaneously. This way the margin distribution is optimized. A totally-corrective optimization algorithm based on column generation is proposed to implement MDBoost. Experiments on UCI datasets show that MDBoost outperforms AdaBoost and LPBoost in most cases.

preprint2010arXiv

Effective Pedestrian Detection Using Center-symmetric Local Binary/Trinary Patterns

Accurately detecting pedestrians in images plays a critically important role in many computer vision applications. Extraction of effective features is the key to this task. Promising features should be discriminative, robust to various variations and easy to compute. In this work, we present novel features, termed dense center-symmetric local binary patterns (CS-LBP) and pyramid center-symmetric local binary/ternary patterns (CS-LBP/LTP), for pedestrian detection. The standard LBP proposed by Ojala et al. \cite{c4} mainly captures the texture information. The proposed CS-LBP feature, in contrast, captures the gradient information and some texture information. Moreover, the proposed dense CS-LBP and the pyramid CS-LBP/LTP are easy to implement and computationally efficient, which is desirable for real-time applications. Experiments on the INRIA pedestrian dataset show that the dense CS-LBP feature with linear supporct vector machines (SVMs) is comparable with the histograms of oriented gradients (HOG) feature with linear SVMs, and the pyramid CS-LBP/LTP features outperform both HOG features with linear SVMs and the start-of-the-art pyramid HOG (PHOG) feature with the histogram intersection kernel SVMs. We also demonstrate that the combination of our pyramid CS-LBP feature and the PHOG feature could significantly improve the detection performance-producing state-of-the-art accuracy on the INRIA pedestrian dataset.

preprint2010arXiv

Face Detection with Effective Feature Extraction

There is an abundant literature on face detection due to its important role in many vision applications. Since Viola and Jones proposed the first real-time AdaBoost based face detector, Haar-like features have been adopted as the method of choice for frontal face detection. In this work, we show that simple features other than Haar-like features can also be applied for training an effective face detector. Since, single feature is not discriminative enough to separate faces from difficult non-faces, we further improve the generalization performance of our simple features by introducing feature co-occurrences. We demonstrate that our proposed features yield a performance improvement compared to Haar-like features. In addition, our findings indicate that features play a crucial role in the ability of the system to generalize.

preprint2010arXiv

Incremental Training of a Detector Using Online Sparse Eigen-decomposition

The ability to efficiently and accurately detect objects plays a very crucial role for many computer vision tasks. Recently, offline object detectors have shown a tremendous success. However, one major drawback of offline techniques is that a complete set of training data has to be collected beforehand. In addition, once learned, an offline detector can not make use of newly arriving data. To alleviate these drawbacks, online learning has been adopted with the following objectives: (1) the technique should be computationally and storage efficient; (2) the updated classifier must maintain its high classification accuracy. In this paper, we propose an effective and efficient framework for learning an adaptive online greedy sparse linear discriminant analysis (GSLDA) model. Unlike many existing online boosting detectors, which usually apply exponential or logistic loss, our online algorithm makes use of LDA's learning criterion that not only aims to maximize the class-separation criterion but also incorporates the asymmetrical property of training data distributions. We provide a better alternative for online boosting algorithms in the context of training a visual object detector. We demonstrate the robustness and efficiency of our methods on handwriting digit and face data sets. Our results confirm that object detection tasks benefit significantly when trained in an online manner.

preprint2010arXiv

LACBoost and FisherBoost: Optimally Building Cascade Classifiers

Object detection is one of the key tasks in computer vision. The cascade framework of Viola and Jones has become the de facto standard. A classifier in each node of the cascade is required to achieve extremely high detection rates, instead of low overall classification error. Although there are a few reported methods addressing this requirement in the context of object detection, there is no a principled feature selection method that explicitly takes into account this asymmetric node learning objective. We provide such a boosting algorithm in this work. It is inspired by the linear asymmetric classifier (LAC) of Wu et al. in that our boosting algorithm optimizes a similar cost function. The new totally-corrective boosting algorithm is implemented by the column generation technique in convex optimization. Experimental results on face detection suggest that our proposed boosting algorithms can improve the state-of-the-art methods in detection performance.

preprint2010arXiv

Optimally Training a Cascade Classifier

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are a few reported methods addressing this requirement in the context of object detection, there is no a principled feature selection method that explicitly takes into account this asymmetric node learning objective. We provide such an algorithm here. We show a special case of the biased minimax probability machine has the same formulation as the linear asymmetric classifier (LAC) of \cite{wu2005linear}. We then design a new boosting algorithm that directly optimizes the cost function of LAC. The resulting totally-corrective boosting algorithm is implemented by the column generation technique in convex optimization. Experimental results on object detection verify the effectiveness of the proposed boosting algorithm as a node classifier in cascade object detection, and show performance better than that of the current state-of-the-art.

preprint2010arXiv

Real-time Visual Tracking Using Sparse Representation

The $\ell_1$ tracker obtains robustness by seeking a sparse representation of the tracking object via $\ell_1$ norm minimization \cite{Xue_ICCV_09_Track}. However, the high computational complexity involved in the $ \ell_1 $ tracker restricts its further applications in real time processing scenario. Hence we propose a Real Time Compressed Sensing Tracking (RTCST) by exploiting the signal recovery power of Compressed Sensing (CS). Dimensionality reduction and a customized Orthogonal Matching Pursuit (OMP) algorithm are adopted to accelerate the CS tracking. As a result, our algorithm achieves a real-time speed that is up to $6,000$ times faster than that of the $\ell_1$ tracker. Meanwhile, RTCST still produces competitive (sometimes even superior) tracking accuracy comparing to the existing $\ell_1$ tracker. Furthermore, for a stationary camera, a further refined tracker is designed by integrating a CS-based background model (CSBM). This CSBM-equipped tracker coined as RTCST-B, outperforms most state-of-the-arts with respect to both accuracy and robustness. Finally, our experimental results on various video sequences, which are verified by a new metric---Tracking Success Probability (TSP), show the excellence of the proposed algorithms.

preprint2010arXiv

Scalable Large-Margin Mahalanobis Distance Metric Learning

For many machine learning algorithms such as $k$-Nearest Neighbor ($k$-NN) classifiers and $ k $-means clustering, often their success heavily depends on the metric used to calculate distances between different data points. An effective solution for defining such a metric is to learn it from a set of labeled training samples. In this work, we propose a fast and scalable algorithm to learn a Mahalanobis distance metric. By employing the principle of margin maximization to achieve better generalization performances, this algorithm formulates the metric learning as a convex optimization problem and a positive semidefinite (psd) matrix is the unknown variable. a specialized gradient descent method is proposed. our algorithm is much more efficient and has a better performance in scalability compared with existing methods. Experiments on benchmark data sets suggest that, compared with state-of-the-art metric learning algorithms, our algorithm can achieve a comparable classification accuracy with reduced computational complexity.

preprint2010arXiv

Totally Corrective Multiclass Boosting with Binary Weak Learners

In this work, we propose a new optimization framework for multiclass boosting learning. In the literature, AdaBoost.MO and AdaBoost.ECC are the two successful multiclass boosting algorithms, which can use binary weak learners. We explicitly derive these two algorithms' Lagrange dual problems based on their regularized loss functions. We show that the Lagrange dual formulations enable us to design totally-corrective multiclass algorithms by using the primal-dual optimization technique. Experiments on benchmark data sets suggest that our multiclass boosting can achieve a comparable generalization capability with state-of-the-art, but the convergence speed is much faster than stage-wise gradient descent boosting. In other words, the new totally corrective algorithms can maximize the margin more aggressively.

Chunhua Shen

What is connected

Connect this record

See the researcher in context

Building this map preview

170 published item(s)

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models

MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection

DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

Efficient Decoder-free Object Detection with Transformers

Efficient Video Segmentation Models with Per-frame Inference

End-to-End Video Text Spotting with Transformer

FreeSOLO: Learning to Segment Objects without Annotations

Improving Monocular Visual Odometry Using Learned Depth

Instance and Panoptic Segmentation Using Conditional Convolutions

PointAttN: You Only Need Attention for Point Cloud Completion

PointInst3D: Segmenting 3D Instances by Points

Poseur: Direct Human Pose Regression with Transformers

PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining

Real-time End-to-End Video Text Spotter with Contrastive Representation Learning

Retrieval Augmented Classification for Long-Tail Visual Recognition

SPTS: Single-Point Text Spotting

Structured Binary Neural Networks for Image Recognition

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching

TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation

DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution

Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection

Object Detection Made Simpler by Eliminating Heuristic NMS

A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification

A Robust Attentional Framework for License Plate Recognition in the Wild

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

Conditional Convolutions for Instance Segmentation

Context Prior for Scene Segmentation

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Efficient Semantic Video Segmentation with Per-frame Inference

From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting

Improving Generative Adversarial Networks with Local Coordinate Coding

Index Network

Joint Deep Learning of Facial Expression Synthesis and Recognition

Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation

Learning Deep Gradient Descent Optimization for Image Deconvolution

Mask Encoding for Single Shot Instance Segmentation

Memorizing Comprehensively to Learn Adaptively: Unsupervised Cross-Domain Person Re-ID with Multi-level Memory

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising

NAS-FCOS: Fast Neural Architecture Search for Object Detection

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

Pairwise Relation Learning for Semi-supervised Gland Segmentation

PolarMask: Single Shot Instance Segmentation with Polar Representation

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Real-time Image Smoothing via Iterative Least Squares

Representative Graph Neural Network

REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments

Scene Text Image Super-Resolution in the Wild

Scope Head for Accurate Localization in Object Detection

Segmenting Transparent Objects in the Wild

Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection

Soft Expert Reward Learning for Vision-and-Language Navigation

SOLO: Segmenting Objects by Locations

StructBoost: Boosting Methods for Predicting Structured Output Variables

Structured Knowledge Distillation for Dense Prediction

Template-Based Automatic Search of Compact Semantic Segmentation Architectures

To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions

Training Quantized Neural Networks with a Full-precision Auxiliary Module

Unsupervised Representation Learning by Predicting Random Distances

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning

Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources

Attend in groups: a weakly-supervised deep learning framework for learning from web data

Bridging Category-level and Instance-level Semantic Image Segmentation

Cross-convolutional-layer Pooling for Image Recognition

Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps