Researcher profile

Yu Qiao

Yu Qiao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computer Vision Artificial Intelligence Computation and Language eess.IV Machine Learning physics.app-ph Robotics cond-mat.stat-mech Databases Human-Computer Interaction Information Retrieval math.RA math.RT Multiagent Systems Neural and Evolutionary Computing physics.class-ph physics.data-an

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

61works

0followers

17topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

preprint2026arXiv

StableI2I: Spotting Unintended Changes in Image-to-Image Transition

In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image preserves the semantic correspondence and spatial structure of the input image. To address this limitation, we propose StableI2I, a unified and dynamic evaluation framework that explicitly measures content fidelity and pre--post consistency across a wide range of I2I tasks without requiring reference images, including image editing and image restoration. In addition, we construct StableI2I-Bench, a benchmark designed to systematically evaluate the accuracy of MLLMs on such fidelity and consistency assessment tasks. Extensive experimental results demonstrate that StableI2I provides accurate, fine-grained, and interpretable evaluations of content fidelity and consistency, with strong correlations to human subjective judgments. Our framework serves as a practical and reliable evaluation tool for diagnosing content consistency and benchmarking model performance in real-world I2I systems.

preprint2026arXiv

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning

Tool-integrated reasoning (TIR) offers a direct way to extend thinking models beyond the limits of text-only reasoning. Paradoxically, we observe that tool-enabled evaluation can degrade reasoning performance even when the strong thinking models make almost no actual tool calls. In this paper, we investigate how to inject natural tool-use behavior into a strong thinking model without sacrificing its no-tool reasoning ability, and present a comprehensive TIR recipe. We highlight that (i) the effectiveness of TIR supervised fine-tuning (SFT) hinges on the learnability of teacher trajectories, which should prioritize problems inherently suited for tool-augmented solutions; (ii) controlling the proportion of tool-use trajectories could mitigate the catastrophic forgetting of text-only reasoning capacity; (iii) optimizing for pass@k and response length instead of training loss could maximize TIR SFT gains while preserving headroom for reinforcement learning (RL) exploration; (iv) a stable RL with verifiable rewards (RLVR) stage, built upon suitable SFT initialization and explicit safeguards against mode collapse, provides a simple yet remarkably effective solution. When applied to Qwen3 thinking models at 4B and 30B scales, our recipe yields models that achieve state-of-the-art performance in a wide range of benchmarks among open-source models, such as 96.7% and 99.2% on AIME 2025 for 4B and 30B, respectively.

preprint2024arXiv

InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words. Our core contribution is to develop a scalable approach to autonomously build a high-quality video-text dataset with large language models (LLM), thereby showcasing its efficacy in learning video-language representation at scale. Specifically, we utilize a multi-scale approach to generate video-related descriptions. Furthermore, we introduce ViCLIP, a video-text representation learning model based on ViT-L. Learned on InternVid via contrastive learning, this model demonstrates leading zero-shot action recognition and competitive video retrieval performance. Beyond basic video understanding tasks like recognition and retrieval, our dataset and model have broad applications. They are particularly beneficial for generating interleaved video-text data for learning a video-centric dialogue system, advancing video-to-text and text-to-video generation research. These proposed resources provide a tool for researchers and practitioners interested in multimodal video understanding and generation.

preprint2024arXiv

VideoChat: Chat-Centric Video Understanding

In this paper, we initiate an attempt of developing an end-to-end chat-centric video understanding system, coined as VideoChat. It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference. To instructively tune this system, we build a video-centric instruction dataset, composed of thousands of videos associated with detailed descriptions and conversations. This dataset emphasizes spatiotemporal reasoning and captures causal relationships, providing a valuable asset for training our chat-centric video understanding system. Preliminary qualitative experiments demonstrate the potential of our system across a broad spectrum of video applications, which could serve as a simple prototype system for future research on chat-centric video understanding. Access our code and data at https://github.com/OpenGVLab/Ask-Anything

preprint2023arXiv

Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields

Common capture low-light scenes are challenging for most computer vision techniques, including Neural Radiance Fields (NeRF). Vanilla NeRF is viewer-centred simplifies the rendering process only as light emission from 3D locations in the viewing direction, thus failing to model the low-illumination induced darkness. Inspired by the emission theory of ancient Greeks that visual perception is accomplished by rays casting from eyes, we make slight modifications on vanilla NeRF to train on multiple views of low-light scenes, we can thus render out the well-lit scene in an unsupervised manner. We introduce a surrogate concept, Concealing Fields, that reduces the transport of light during the volume rendering stage. Specifically, our proposed method, Aleth-NeRF, directly learns from the dark image to understand volumetric object representation and concealing field under priors. By simply eliminating Concealing Fields, we can render a single or multi-view well-lit image(s) and gain superior performance over other 2D low-light enhancement methods. Additionally, we collect the first paired LOw-light and normal-light Multi-view (LOM) datasets for future research. This version is invalid, please refer to our new AAAI version: arXiv:2312.09093

preprint2023arXiv

On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets

There is an emerging line of research on multimodal instruction tuning, and a line of benchmarks has been proposed for evaluating these models recently. Instead of evaluating the models directly, in this paper, we try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets. Also, we seek the way of building a dataset for developing an all-powerful VLIT model, which we believe could also be of utility for establishing a grounded protocol for benchmarking VLIT models. For effective evaluation of VLIT datasets that remains an open question, we propose a tune-cross-evaluation paradigm: tuning on one dataset and evaluating on the others in turn. For each single tune-evaluation experiment set, we define the Meta Quality (MQ) as the mean score obtained by a set of caption metrics including BLEU, METEOR, and ROUGE-L to quantify the quality of a certain dataset or a sample. On this basis, to evaluate the comprehensiveness of a dataset, we develop the Dataset Quality (DQ) covering all tune-evaluation sets. To lay the foundation for building a comprehensive dataset and developing an all-powerful model for practical applications, we define the Sample Quality (SQ) to quantify the all-sided quality of each sample. Extensive experiments validate the rationality of the proposed evaluation paradigm. Based on the holistic evaluation, we build a new dataset, REVO-LION (REfining VisiOn-Language InstructiOn tuNing), by collecting samples with higher SQ from each dataset. Remarkably, even with only half of the complete data, the model trained on REVO-LION can achieve the performance comparable to simply adding all VLIT datasets up. Furthermore, REVO-LION not only facilitates the development of a powerful model but also incorporates an evaluation set, which is designed to serve as a convenient benchmark for future research in the field.

preprint2022arXiv

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

Large-scale datasets play a vital role in computer vision. But current datasets are annotated blindly without differentiation to samples, making the data collection inefficient and unscalable. The open question is how to build a mega-scale dataset actively. Although advanced active learning algorithms might be the answer, we experimentally found that they are lame in the realistic annotation scenario where out-of-distribution data is extensive. This work thus proposes a novel active learning framework for realistic dataset annotation. Equipped with this framework, we build a high-quality vision dataset -- Bamboo, which consists of 69M image classification annotations with 119K categories and 28M object bounding box annotations with 809 categories. We organize these categories by a hierarchical taxonomy integrated from several knowledge bases. The classification annotations are four times larger than ImageNet22K, and that of detection is three times larger than Object365. Compared to ImageNet22K and Objects365, models pre-trained on Bamboo achieve superior performance among various downstream tasks (6.2% gains on classification and 2.1% gains on detection). We believe our active learning framework and Bamboo are essential for future work.

preprint2022arXiv

Blueprint Separable Residual Network for Efficient Image Super-Resolution

Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply in edge devices. To alleviate this problem, many novel and effective solutions have been proposed. Convolutional neural network (CNN) with the attention mechanism has attracted increasing attention due to its efficiency and effectiveness. However, there is still redundancy in the convolution operation. In this paper, we propose Blueprint Separable Residual Network (BSRN) containing two efficient designs. One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation. The other is to enhance the model ability by introducing more effective attention modules. The experimental results show that BSRN achieves state-of-the-art performance among existing efficient SR methods. Moreover, a smaller variant of our model BSRN-S won the first place in model complexity track of NTIRE 2022 Efficient SR Challenge. The code is available at https://github.com/xiaom233/BSRN.

preprint2022arXiv

Cohomology and deformations of Relative Rota-Baxter operators on Lie-Yamaguti algebras

In this paper, we establish the cohomology of relative Rota-Baxter operators on Lie-Yamaguti algebras via the Yamaguti cohomology. Then we use this type of cohomology to characterize deformations of relative Rota-Baxter operators on Lie-Yamaguti algebras. We show that if two linear or formal deformations of a relative Rota-Baxter operator are equivalent, then their infinitesimals are in the same cohomology class in the first cohomology group. Moreover, an order $n$ deformation of a relative Rota-Baxter operator can be extended to an order $n+1$ deformation if and only if the obstruction class in the second cohomology group is trivial.

preprint2022arXiv

ConvMAE: Masked Convolution Meets Masked Autoencoders

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation. In this paper, our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. However, directly using the original masking strategy leads to the heavy computational cost and pretraining-finetuning discrepancy. To tackle the issue, we adopt the masked convolution to prevent information leakage in the convolution blocks. A simple block-wise masking strategy is proposed to ensure computational efficiency. We also propose to more directly supervise the multi-scale features of the encoder to boost multi-scale features. Based on our pretrained ConvMAE models, ConvMAE-Base improves ImageNet-1K finetuning accuracy by 1.4% compared with MAE-Base. On object detection, ConvMAE-Base finetuned for only 25 epochs surpasses MAE-Base fined-tuned for 100 epochs by 2.9% box AP and 2.2% mask AP respectively. Code and pretrained models are available at https://github.com/Alpha-VL/ConvMAE.

preprint2022arXiv

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

Self-supervised learning has not been fully explored for point cloud analysis. Current frameworks are mainly based on point cloud reconstruction. Given only 3D coordinates, such approaches tend to learn local geometric structures and contours, while failing in understanding high level semantic content. Consequently, they achieve unsatisfactory performance in downstream tasks such as classification, segmentation, etc. To fill this gap, we propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud, and thus promote discriminative power of point cloud representation. First, we introduce a concise contour-perturbed augmentation module for point cloud reconstruction. With guidance of geometry disentangling, we divide point cloud into contour and content components. Subsequently, we perturb the contour components and preserve the content components on the point cloud. As a result, self supervisor can effectively focus on semantic content, by reconstructing the original point cloud from such perturbed one. Second, we use this perturbed reconstruction as an assistant branch, to guide the learning of basic reconstruction branch via a distinct dual-branch consistency loss. In this case, our CP-Net not only captures structural contour but also learn semantic content for discriminative downstream tasks. Finally, we perform extensive experiments on a number of point cloud benchmarks. Part segmentation results demonstrate that our CP-Net (81.5% of mIoU) outperforms the previous self-supervised models, and narrows the gap with the fully-supervised methods. For classification, we get a competitive result with the fully-supervised methods on ModelNet40 (92.5% accuracy) and ScanObjectNN (87.9% accuracy). The codes and models will be released afterwards.

preprint2022arXiv

CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative Panoptic-Regional Active Learning framework (CPRAL) to address the semantic segmentation task. For a small batch of images initially sampled with pixel-wise annotations, we employ panoptic information to initially select unlabeled samples. Considering the class imbalance in the segmentation dataset, we import a Regional Gaussian Attention module (RGA) to achieve semantics-biased selection. The subset is highlighted by vote entropy and then attended by Gaussian kernels to maximize the biased regions. We also propose a Contextual Labels Extension (CLE) to boost regional annotations with contextual attention guidance. With the collaboration of semantics-agnostic panoptic matching and regionbiased selection and extension, our CPRAL can strike a balance between labeling efforts and performance and compromise the semantics distribution. We perform extensive experiments on Cityscapes and BDD10K datasets and show that CPRAL outperforms the cutting-edge methods with impressive results and less labeling proportion.

preprint2022arXiv

Discovering Distinctive "Semantics" in Super-Resolution Networks

Image super-resolution (SR) is a representative low-level vision problem. Although deep SR networks have achieved extraordinary success, we are still unaware of their working mechanisms. Specifically, whether SR networks can learn semantic information, or just perform complex mapping function? What hinders SR networks from generalizing to real-world data? These questions not only raise our curiosity, but also influence SR network development. In this paper, we make the primary attempt to answer the above fundamental questions. After comprehensively analyzing the feature representations (via dimensionality reduction and visualization), we successfully discover the distinctive "semantics" in SR networks, i.e., deep degradation representations (DDR), which relate to image degradation instead of image content. We show that a well-trained deep SR network is naturally a good descriptor of degradation information. Our experiments also reveal two key factors (adversarial learning and global residual) that influence the extraction of such semantics. We further apply DDR in several interesting applications (such as distortion identification, blind SR and generalization evaluation) and achieve promising results, demonstrating the correctness and effectiveness of our findings.

preprint2022arXiv

Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning

In this paper, we propose a simple and general framework for self-supervised point cloud representation learning. Human beings understand the 3D world by extracting two levels of information and establishing the relationship between them. One is the global shape of an object, and the other is the local structures of it. However, few existing studies in point cloud representation learning explored how to learn both global shapes and local-to-global relationships without a specified network architecture. Inspired by how human beings understand the world, we utilize knowledge distillation to learn both global shape information and the relationship between global shape and local structures. At the same time, we combine contrastive learning with knowledge distillation to make the teacher network be better updated. Our method achieves the state-of-the-art performance on linear classification and multiple other downstream tasks. Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method. Our code will be released soon.

preprint2022arXiv

Domain Generalization: A Survey

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d.~assumption on source/target data, which is often violated in practice due to domain shift. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Over the last ten years, research in DG has made great progress, leading to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, to name a few; DG has also been studied in various application areas including computer vision, speech recognition, natural language processing, medical imaging, and reinforcement learning. In this paper, for the first time a comprehensive literature review in DG is provided to summarize the developments over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other relevant fields like domain adaptation and transfer learning. Then, we conduct a thorough review into existing methods and theories. Finally, we conclude this survey with insights and discussions on future research directions.

preprint2022arXiv

Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition

Learning spatial-temporal relation among multiple actors is crucial for group activity recognition. Different group activities often show the diversified interactions between actors in the video. Hence, it is often difficult to model complex group activities from a single view of spatial-temporal actor evolution. To tackle this problem, we propose a distinct Dual-path Actor Interaction (DualAI) framework, which flexibly arranges spatial and temporal transformers in two complementary orders, enhancing actor relations by integrating merits from different spatiotemporal paths. Moreover, we introduce a novel Multi-scale Actor Contrastive Loss (MAC-Loss) between two interactive paths of Dual-AI. Via self-supervised actor consistency in both frame and video levels, MAC-Loss can effectively distinguish individual actor representations to reduce action confusion among different actors. Consequently, our Dual-AI can boost group activity recognition by fusing such discriminative features of different actors. To evaluate the proposed approach, we conduct extensive experiments on the widely used benchmarks, including Volleyball, Collective Activity, and NBA datasets. The proposed Dual-AI achieves state-of-the-art performance on all these datasets. It is worth noting the proposed Dual-AI with 50% training data outperforms a number of recent approaches with 100% training data. This confirms the generalization power of Dual-AI for group activity recognition, even under the challenging scenarios of limited supervision.

preprint2022arXiv

Frozen CLIP Models are Efficient Video Learners

Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos. This enables the video network to benefit from the pretrained image model. However, this requires substantial computation and memory resources for finetuning on videos and the alternative of directly using pretrained image features without finetuning the image backbone leads to subpar results. Fortunately, recent advances in Contrastive Vision-Language Pre-training (CLIP) pave the way for a new route for visual recognition tasks. Pretrained on large open-vocabulary image-text pair data, these models learn powerful visual representations with rich semantics. In this paper, we present Efficient Video Learning (EVL) -- an efficient framework for directly training high-quality video recognition models with frozen CLIP features. Specifically, we employ a lightweight Transformer decoder and learn a query token to dynamically collect frame-level spatial features from the CLIP image encoder. Furthermore, we adopt a local temporal module in each decoder layer to discover temporal clues from adjacent frames and their attention maps. We show that despite being efficient to train with a frozen backbone, our models learn high quality video representations on a variety of video recognition datasets. Code is available at https://github.com/OpenGVLab/efficient-video-recognition.

preprint2022arXiv

GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation

Automatic artistic text generation is an emerging topic which receives increasing attention due to its wide applications. The artistic text can be divided into three components, content, font, and texture, respectively. Existing artistic text generation models usually focus on manipulating one aspect of the above components, which is a sub-optimal solution for controllable general artistic text generation. To remedy this issue, we propose a novel approach, namely GenText, to achieve general artistic text style transfer by separably migrating the font and texture styles from the different source images to the target images in an unsupervised manner. Specifically, our current work incorporates three different stages, stylization, destylization, and font transfer, respectively, into a unified platform with a single powerful encoder network and two separate style generator networks, one for font transfer, the other for stylization and destylization. The destylization stage first extracts the font style of the font reference image, then the font transfer stage generates the target content with the desired font style. Finally, the stylization stage renders the resulted font image with respect to the texture style in the reference image. Moreover, considering the difficult data acquisition of paired artistic text images, our model is designed under the unsupervised setting, where all stages can be effectively optimized from unpaired data. Qualitative and quantitative results are performed on artistic text benchmarks, which demonstrate the superior performance of our proposed model. The code with models will become publicly available in the future.

preprint2022arXiv

HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints

The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i.e., feature vectors) and structured (i.e., related attributes) constraints. In this paper, we present HQANN, a simple yet highly efficient hybrid query processing framework which can be easily embedded into existing proximity graph-based ANNS algorithms. We guarantee both low latency and high recall by leveraging navigation sense among attributes and fusing vector similarity search with attribute filtering. Experimental results on both public and in-house datasets demonstrate that HQANN is 10x faster than the state-of-the-art hybrid ANNS solutions to reach the same recall quality and its performance is hardly affected by the complexity of attributes. It can reach 99\% recall@10 in just around 50 microseconds On GLOVE-1.2M with thousands of attribute constraints.

preprint2022arXiv

INTERN: A New Learning Paradigm Towards General Vision

Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However, down the road, a key challenge awaits us, that is, our capability of meeting rapidly-growing scenario-specific demands is severely limited by the cost of acquiring a commensurate amount of training data. This difficult situation is in essence due to limitations of the mainstream learning paradigm: we need to train a new model for each new scenario, based on a large quantity of well-annotated data and commonly from scratch. In tackling this fundamental problem, we move beyond and develop a new learning paradigm named INTERN. By learning with supervisory signals from multiple sources in multiple stages, the model being trained will develop strong generalizability. We evaluate our model on 26 well-known datasets that cover four categories of tasks in computer vision. In most cases, our models, adapted with only 10% of the training data in the target domain, outperform the counterparts trained with the full set of data, often by a significant margin. This is an important step towards a promising prospect where such a model with general vision capability can dramatically reduce our reliance on data, thus expediting the adoption of AI technologies. Furthermore, revolving around our new paradigm, we also introduce a new data system, a new architecture, and a new benchmark, which, together, form a general vision ecosystem to support its future development in an open and inclusive manner. See project website at https://opengvlab.shlab.org.cn .

preprint2022arXiv

Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot

Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design. Though these sensors have laid a solid foundation, most massive-production solutions up to date still fall into L2 phase. Among these, Comma.ai comes to our sight, claiming one $999 aftermarket device mounted with a single camera and board inside owns the ability to handle L2 scenarios. Together with open-sourced software of the entire system released by Comma.ai, the project is named Openpilot. Is it possible? If so, how is it made possible? With curiosity in mind, we deep-dive into Openpilot and conclude that its key to success is the end-to-end system design instead of a conventional modular framework. The model is briefed as Supercombo, and it can predict the ego vehicle's future trajectory and other road semantics on the fly from monocular input. Unfortunately, the training process and massive amount of data to make all these work are not publicly available. To achieve an intensive investigation, we try to reimplement the training details and test the pipeline on public benchmarks. The refactored network proposed in this work is referred to as OP-Deepdive. For a fair comparison of our version to the original Supercombo, we introduce a dual-model deployment scheme to test the driving performance in the real world. Experimental results on nuScenes, Comma2k19, CARLA, and in-house realistic scenarios verify that a low-cost device can indeed achieve most L2 functionalities and be on par with the original Supercombo model. In this report, we would like to share our latest findings, shed some light on the new perspective of end-to-end autonomous driving from an industrial product-level side, and potentially inspire the community to continue improving the performance. Our code, benchmarks are at https://github.com/OpenPerceptionX/Openpilot-Deepdive.

preprint2022arXiv

Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns

There is a growing interest in the combined use of NLP and machine learning methods to predict gaze patterns during naturalistic reading. While promising results have been obtained through the use of transformer-based language models, little work has been undertaken to relate the performance of such models to general text characteristics. In this paper we report on experiments with two eye-tracking corpora of naturalistic reading and two language models (BERT and GPT-2). In all experiments, we test effects of a broad spectrum of features for predicting human reading behavior that fall into five categories (syntactic complexity, lexical richness, register-based multiword combinations, readability and psycholinguistic word properties). Our experiments show that both the features included and the architecture of the transformer-based language models play a role in predicting multiple eye-tracking measures during naturalistic reading. We also report the results of experiments aimed at determining the relative importance of features from different groups using SP-LIME.

preprint2022arXiv

MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning

Recently, MLP-Like networks have been revived for image recognition. However, whether it is possible to build a generic MLP-Like architecture on video domain has not been explored, due to complex spatial-temporal modeling with large computation burden. To fill this gap, we present an efficient self-attention free backbone, namely MorphMLP, which flexibly leverages the concise Fully-Connected (FC) layer for video representation learning. Specifically, a MorphMLP block consists of two key layers in sequence, i.e., MorphFC_s and MorphFC_t, for spatial and temporal modeling respectively. MorphFC_s can effectively capture core semantics in each frame, by progressive token interaction along both height and width dimensions. Alternatively, MorphFC_t can adaptively learn long-term dependency over frames, by temporal token aggregation on each spatial location. With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance. Finally, we evaluate our MorphMLP on a number of popular video benchmarks. Compared with the recent state-of-the-art models, MorphMLP significantly reduces computation but with better accuracy, e.g., MorphMLP-S only uses 50% GFLOPs of VideoSwin-T but achieves 0.9% top-1 improvement on Kinetics400, under ImageNet1K pretraining. MorphMLP-B only uses 43% GFLOPs of MViT-B but achieves 2.4% top-1 improvement on SSV2, even though MorphMLP-B is pretrained on ImageNet1K while MViT-B is pretrained on Kinetics400. Moreover, our method adapted to the image domain outperforms previous SOTA MLP-Like architectures. Code is available at https://github.com/MTLab/MorphMLP.

preprint2022arXiv

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.

preprint2022arXiv

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.). Previous work struggled in complex cases due to their simple designs of the spatial transformation between front view and bird's eye view (BEV) and the lack of a realistic dataset. Towards these issues, we present PersFormer: an end-to-end monocular 3D lane detector with a novel Transformer-based spatial feature transformation module. Our model generates BEV features by attending to related front-view local regions with camera parameters as a reference. PersFormer adopts a unified 2D/3D anchor design and an auxiliary task to detect 2D/3D lanes simultaneously, enhancing the feature consistency and sharing the benefits of multi-task learning. Moreover, we release one of the first large-scale real-world 3D lane datasets: OpenLane, with high-quality annotation and scenario diversity. OpenLane contains 200,000 frames, over 880,000 instance-level lanes, 14 lane categories, along with scene tags and the closed-in-path object annotations to encourage the development of lane detection and more industrial-related autonomous driving methods. We show that PersFormer significantly outperforms competitive baselines in the 3D lane detection task on our new OpenLane dataset as well as Apollo 3D Lane Synthetic dataset, and is also on par with state-of-the-art algorithms in the 2D task on OpenLane. The project page is available at https://github.com/OpenPerceptionX/PersFormer_3DLane and OpenLane dataset is provided at https://github.com/OpenPerceptionX/OpenLane.

preprint2022arXiv

POS-BERT: Point Cloud One-Stage BERT Pre-Training

Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires training a fixed discrete Variational AutoEncoder (dVAE) before pre-training, which results in a complex two-stage method called Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the mask patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patches information under the supervision of the corresponding tokenizer output. Unlike Point-BERT, its tokenizer is extra-trained and frozen. We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process. Further, in order to learn high-level semantic representation, we combine contrastive learning to maximize the class token consistency between different transformation point clouds. Extensive experiments have demonstrated that POS-BERT can extract high-quality pre-training features and promote downstream tasks to improve performance. Using the pre-training model without any fine-tuning to extract features and train linear SVM on ModelNet40, POS-BERT achieves the state-of-the-art classification accuracy, which exceeds Point-BERT by 3.5\%. In addition, our approach has significantly improved many downstream tasks, such as fine-tuned classification, few-shot classification, part segmentation. The code and trained-models will be available at: \url{https://github.com/fukexue/POS-BERT}.

preprint2022arXiv

Producing Useful Work in a Cycle by Absorbing Heat from a Single Thermal Reservoir: An Investigation on a Locally Nonchaotic Energy Barrier

In the current research, we investigate the concept of spontaneously nonequilibrium dimension (SND), and show that a SND-based system can break the second law of thermodynamics. The main characteristic of the SND is the inherent nonequilibrium particle crossing ratio. A locally nonchaotic energy barrier is employed to form the model system. On the one hand, when the barrier width is much smaller than the mean free path of the particles, the system cannot reach thermodynamic equilibrium; on the other hand, the nonequilibrium particle distribution allows for production of useful work in a cycle by absorbing heat from a single thermal reservoir. Such system performance is demonstrated by a Monte Carlo simulation. It should be attributed to the unbalanced cross-influence of the thermally correlated thermodynamic forces, incompatible with the conventional framework of statistical mechanics. No Maxwell's demon is involved. Similar effects may be achieved by a number of variants, e.g., when the barrier is switchable or there are distributed nonchaotic traps.

preprint2022arXiv

Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features

Research at the intersection of personality psychology, computer science, and linguistics has recently focused increasingly on modeling and predicting personality from language use. We report two major improvements in predicting personality traits from text data: (1) to our knowledge, the most comprehensive set of theory-based psycholinguistic features and (2) hybrid models that integrate a pre-trained Transformer Language Model BERT and Bidirectional Long Short-Term Memory (BLSTM) networks trained on within-text distributions ('text contours') of psycholinguistic features. We experiment with BLSTM models (with and without Attention) and with two techniques for applying pre-trained language representations from the transformer model - 'feature-based' and 'fine-tuning'. We evaluate the performance of the models we built on two benchmark datasets that target the two dominant theoretical models of personality: the Big Five Essay dataset and the MBTI Kaggle dataset. Our results are encouraging as our models outperform existing work on the same datasets. More specifically, our models achieve improvement in classification accuracy by 2.9% on the Essay dataset and 8.28% on the Kaggle MBTI dataset. In addition, we perform ablation experiments to quantify the impact of different categories of psycholinguistic features in the respective personality prediction models.

preprint2022arXiv

Reflash Dropout in Image Super-Resolution

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools -- one is from recent network interpretation works, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks.

preprint2022arXiv

Self-slimmed Vision Transformer

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bring a huge computation burden, because of the exhausting token-to-token comparison. The previous works focus on dropping insignificant tokens to reduce the computational cost of ViTs. But when the dropping ratio increases, this hard manner will inevitably discard the vital tokens, which limits its efficiency. To solve the issue, we propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation. As a general method of token hard dropping, our TSM softly integrates redundant tokens into fewer informative ones. It can dynamically zoom visual attention without cutting off discriminative token relations in the images, even with a high slimming ratio. Furthermore, we introduce a concise Feature Recalibration Distillation (FRD) framework, wherein we design a reverse version of TSM (RTSM) to recalibrate the unstructured token in a flexible auto-encoder manner. Due to the similar structure between teacher and student, our FRD can effectively leverage structure knowledge for better convergence. Finally, we conduct extensive experiments to evaluate our SiT. It demonstrates that our method can speed up ViTs by 1.7x with negligible accuracy drop, and even speed up ViTs by 3.6x while maintaining 97% of their performance. Surprisingly, by simply arming LV-ViT with our SiT, we achieve new state-of-the-art performance on ImageNet. Code is available at https://github.com/Sense-X/SiT.

preprint2022arXiv

Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge transfer. To further enhance CLIP's adaption capability, existing methods proposed to fine-tune additional learnable modules, which significantly improves the few-shot performance but introduces extra training time and computational resources. In this paper, we propose a training-free adaption method for CLIP to conduct few-shot classification, termed as Tip-Adapter, which not only inherits the training-free advantage of zero-shot CLIP but also performs comparably to those training-required approaches. Tip-Adapter constructs the adapter via a key-value cache model from the few-shot training set, and updates the prior knowledge encoded in CLIP by feature retrieval. On top of that, the performance of Tip-Adapter can be further boosted to be state-of-the-art on ImageNet by fine-tuning the cache model for 10$\times$ fewer epochs than existing methods, which is both effective and efficient. We conduct extensive experiments of few-shot classification on 11 datasets to demonstrate the superiority of our proposed methods. Code is released at https://github.com/gaopengcuhk/Tip-Adapter.

preprint2022arXiv

UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been mainly driven by 3D convolutional neural networks and vision transformers. Although 3D convolution can efficiently aggregate local context to suppress local redundancy from a small 3D neighborhood, it lacks the capability to capture global dependency because of the limited receptive field. Alternatively, vision transformers can effectively capture long-range dependency by self-attention mechanism, while having the limitation on reducing local redundancy with blind similarity comparison among all the tokens in each layer. Based on these observations, we propose a novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy. Different from traditional transformers, our relation aggregator can tackle both spatiotemporal redundancy and dependency, by learning local and global token affinity respectively in shallow and deep layers. We conduct extensive experiments on the popular video benchmarks, e.g., Kinetics-400, Kinetics-600, and Something-Something V1&V2. With only ImageNet-1K pretraining, our UniFormer achieves 82.9%/84.8% top-1 accuracy on Kinetics-400/Kinetics-600, while requiring 10x fewer GFLOPs than other state-of-the-art methods. For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60.9% and 71.2% top-1 accuracy respectively. Code is available at https://github.com/Sense-X/UniFormer.

preprint2022arXiv

Very Lightweight Photo Retouching Network with Conditional Sequential Modulation

Photo retouching aims at improving the aesthetic visual quality of images that suffer from photographic defects, especially for poor contrast, over/under exposure, and inharmonious saturation. In practice, photo retouching can be accomplished by a series of image processing operations. As most commonly-used retouching operations are pixel-independent, i.e., the manipulation on one pixel is uncorrelated with its neighboring pixels, we can take advantage of this property and design a specialized algorithm for efficient global photo retouching. We analyze these global operations and find that they can be mathematically formulated by a Multi-Layer Perceptron (MLP). Based on this observation, we propose an extremely lightweight framework -- Conditional Sequential Retouching Network (CSRNet). Benefiting from the utilization of $1\times1$ convolution, CSRNet only contains less than 37K trainable parameters, which are orders of magnitude smaller than existing learning-based methods. Experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. In addition to achieve global photo retouching, the proposed framework can be easily extended to learn local enhancement effects. The extended model, namely CSRNet-L, also achieves competitive results in various local enhancement tasks. Codes are available at https://github.com/lyh-18/CSRNet.

preprint2022arXiv

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning to deal with the class imbalance problem, based on the image modality. In this work, we present a visual-linguistic long-tailed recognition framework, termed VL-LTR, and conduct empirical studies on the benefits of introducing text modality for long-tailed recognition (LTR). Compared to existing approaches, the proposed VL-LTR has the following merits. (1) Our method can not only learn visual representation from images but also learn corresponding linguistic representation from noisy class-level text descriptions collected from the Internet; (2) Our method can effectively use the learned visual-linguistic representation to improve the visual recognition performance, especially for classes with fewer image samples. We also conduct extensive experiments and set the new state-of-the-art performance on widely-used LTR benchmarks. Notably, our method achieves 77.2% overall accuracy on ImageNet-LT, which significantly outperforms the previous best method by over 17 points, and is close to the prevailing performance training on the full ImageNet. Code is available at https://github.com/ChangyaoTian/VL-LTR.

preprint2022arXiv

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

In computer vision, pre-training models based on largescale supervised learning have been proven effective over the past few years. However, existing works mostly focus on learning from individual task with single data source (e.g., ImageNet for classification or COCO for detection). This restricted form limits their generalizability and usability due to the lack of vast semantic information from various tasks and data sources. Here, we demonstrate that jointly learning from heterogeneous tasks and multiple data sources contributes to universal visual representation, leading to better transferring results of various downstream tasks. Thus, learning how to bridge the gaps among different tasks and data sources is the key, but it still remains an open question. In this work, we propose a representation learning framework called X-Learner, which learns the universal feature of multiple vision tasks supervised by various sources, with expansion and squeeze stage: 1) Expansion Stage: X-Learner learns the task-specific feature to alleviate task interference and enrich the representation by reconciliation layer. 2) Squeeze Stage: X-Learner condenses the model to a reasonable size and learns the universal and generalizable representation for various tasks transferring. Extensive experiments demonstrate that X-Learner achieves strong performance on different tasks without extra annotations, modalities and computational costs compared to existing representation learning methods. Notably, a single X-Learner model shows remarkable gains of 3.0%, 3.3% and 1.8% over current pretrained models on 12 downstream datasets for classification, object detection and semantic segmentation.

preprint2021arXiv

Affordance Transfer Learning for Human-Object Interaction Detection

Reasoning the human-object interactions (HOI) is essential for deeper scene understanding, while object affordances (or functionalities) are of great importance for human to discover unseen HOIs with novel objects. Inspired by this, we introduce an affordance transfer learning approach to jointly detect HOIs with novel objects and recognize affordances. Specifically, HOI representations can be decoupled into a combination of affordance and object representations, making it possible to compose novel interactions by combining affordance representations and novel object representations from additional images, i.e. transferring the affordance to novel objects. With the proposed affordance transfer learning, the model is also capable of inferring the affordances of novel objects from known affordance representations. The proposed method can thus be used to 1) improve the performance of HOI detection, especially for the HOIs with unseen objects; and 2) infer the affordances of novel objects. Experimental results on two datasets, HICO-DET and HOI-COCO (from V-COCO), demonstrate significant improvements over recent state-of-the-art methods for HOI detection and object affordance detection. Code is available at https://github.com/zhihou7/HOI-CL

preprint2021arXiv

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation

Generating human action proposals in untrimmed videos is an important yet challenging task with wide applications. Current methods often suffer from the noisy boundary locations and the inferior quality of confidence scores used for proposal retrieving. In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation. First, we propose a novel boundary regressor based on the complementary characteristics of both starting and ending boundary classifiers. Specifically, we utilize the U-shaped architecture with nested skip connections to capture rich contexts and introduce bi-directional boundary matching mechanism to improve boundary precision. Second, to account for the proposal-proposal relations ignored in previous methods, we devise a proposal relation block to which includes two self-attention modules from the aspects of position and channel. Furthermore, we find that there inevitably exists data imbalanced problems in the positive/negative proposals and temporal durations, which harm the model performance on tail distributions. To relieve this issue, we introduce the scale-balanced re-sampling strategy. Extensive experiments are conducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, which demonstrate that BSN++ achieves the state-of-the-art performance. Not surprisingly, the proposed BSN++ ranked 1st place in the CVPR19 - ActivityNet challenge leaderboard on temporal action localization task.

preprint2021arXiv

ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large images are usually decomposed into small sub-images in practical usages. Based on this processing, we found that different image regions have different restoration difficulties and can be processed by networks with different capacities. Intuitively, smooth areas are easier to super-solve than complex textures. To utilize this property, we can adopt appropriate SR networks to process different sub-images after the decomposition. On this basis, we propose a new solution pipeline -- ClassSR that combines classification and SR in a unified framework. In particular, it first uses a Class-Module to classify the sub-images into different classes according to restoration difficulties, then applies an SR-Module to perform SR for different classes. The Class-Module is a conventional classification network, while the SR-Module is a network container that consists of the to-be-accelerated SR network and its simplified versions. We further introduce a new classification method with two losses -- Class-Loss and Average-Loss to produce the classification results. After joint training, a majority of sub-images will pass through smaller networks, thus the computational cost can be significantly reduced. Experiments show that our ClassSR can help most existing methods (e.g., FSRCNN, CARN, SRResNet, RCAN) save up to 50% FLOPs on DIV8K datasets. This general framework can also be applied in other low-level vision tasks.

preprint2021arXiv

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

In 2D image processing, some attempts decompose images into high and low frequency components for describing edge and smooth parts respectively. Similarly, the contour and flat area of 3D objects, such as the boundary and seat area of a chair, describe different but also complementary geometries. However, such investigation is lost in previous deep networks that understand point clouds by directly treating all points or local patches equally. To solve this problem, we propose Geometry-Disentangled Attention Network (GDANet). GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Then GDANet exploits Sharp-Gentle Complementary Attention Module that regards the features from sharp and gentle variation components as two holistic representations, and pays different attentions to them while fusing them respectively with original point cloud features. In this way, our method captures and refines the holistic and complementary 3D geometric semantics from two distinct disentangled components to supplement the local information. Extensive experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters. Code is released on https://github.com/mutianxu/GDANet.

preprint2021arXiv

Multi-scale Information Assembly for Image Matting

Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different-level information, including the central bodies, large-grained boundaries, refined details, etc. Based on this observation, in this paper, we propose a multi-scale information assembly framework (MSIA-matte) to pull out high-quality alpha mattes from single RGB images. Technically speaking, given an input image, we extract advanced semantics as our subject content and retain initial CNN features to encode different-level foreground expression, then combine them by our well-designed information assembly strategy. Extensive experiments can prove the effectiveness of the proposed MSIA-matte, and we can achieve state-of-the-art performance compared to most existing matting networks.

preprint2021arXiv

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering

Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations across disjoint camera views. In this paper, we address the unsupervised person Re-ID with a conceptually novel yet simple framework, termed as Multi-label Learning guided self-paced Clustering (MLC). MLC mainly learns discriminative features with three crucial modules, namely a multi-scale network, a multi-label learning module, and a self-paced clustering module. Specifically, the multi-scale network generates multi-granularity person features in both global and local views. The multi-label learning module leverages a memory feature bank and assigns each image with a multi-label vector based on the similarities between the image and feature bank. After multi-label training for several epochs, the self-paced clustering joins in training and assigns a pseudo label for each image. The benefits of our MLC come from three aspects: i) the multi-scale person features for better similarity measurement, ii) the multi-label assignment based on the whole dataset ensures that every image can be trained, and iii) the self-paced clustering removes some noisy samples for better feature learning. Extensive experiments on three popular large-scale Re-ID benchmarks demonstrate that our MLC outperforms previous state-of-the-art methods and significantly improves the performance of unsupervised person Re-ID.

preprint2020arXiv

A Comprehensive Study on Temporal Modeling for Online Action Detection

Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. A typical OAD system mainly consists of three modules: a frame-level feature extractor which is usually based on pre-trained deep Convolutional Neural Networks (CNNs), a temporal modeling module, and an action classifier. Among them, the temporal modeling module is crucial which aggregates discriminative information from historical and current features. Though many temporal modeling methods have been developed for OAD and other topics, their effects are lack of investigation on OAD fairly. This paper aims to provide a comprehensive study on temporal modeling for OAD including four meta types of temporal modeling methods, \ie temporal pooling, temporal convolution, recurrent neural networks, and temporal attention, and uncover some good practices to produce a state-of-the-art OAD system. Many of them are explored in OAD for the first time, and extensively evaluated with various hyper parameters. Furthermore, based on our comprehensive study, we present several hybrid temporal modeling methods, which outperform the recent state-of-the-art methods with sizable margins on THUMOS-14 and TVSeries.

preprint2020arXiv

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution.

preprint2020arXiv

Algae-Filler Artificial Timber with an Ultralow Binder Content

Algae cultivation is an active area of study for carbon sequestration, while the large amount of produced algae must be upcycled. In the current study, we fabricated artificial timber based on algae filler, with only 2~4% epoxy binder. The flexural strength could be comparable with those of softwoods. The binder was efficiently dispersed in the algae phase through diluent-aided compaction self-assembly. The important processing parameters included the binder content, the filler morphology, the compaction pressure, the diluent ratio, and the curing condition. This research not only is critical to carbon sequestration, but also helps reduce the consumption of conventional construction materials.

preprint2020arXiv

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification

Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledge, all the existing benchmarks assume the same person will have the same clothes. While in real-world scenarios, it is very often for a person to change clothes. To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes. COCAS totally contains 62,382 body images from 5,266 persons. Based on COCAS, we introduce a new person re-id setting for clothes changing problem, where the query includes both a clothes template and a person image taking another clothes. Moreover, we propose a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under our setting. Experiments show that it is feasible for clothes changing re-id with clothes templates.

preprint2020arXiv

Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition

Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational resources, which hinders their applications in practice. Existing knowledge distillation methods are limited to the image-level spatial domain, ignoring the temporal and frequency information which provide structural knowledge and are important for video analysis. This paper explores how to train small and efficient networks for action recognition. Specifically, we propose two distillation strategies in the frequency domain, namely the feature spectrum and parameter distribution distillations respectively. Our insight is that appealing performance of action recognition requires \textit{explicitly} modeling the temporal frequency spectrum of video features. Therefore, we introduce a spectrum loss that enforces the student network to mimic the temporal frequency spectrum from the teacher network, instead of \textit{implicitly} distilling features as many previous works. Second, the parameter frequency distribution is further adopted to guide the student network to learn the appearance modeling process from the teacher. Besides, a collaborative learning strategy is presented to optimize the training process from a probabilistic view. Extensive experiments are conducted on several action recognition benchmarks, such as Kinetics, Something-Something, and Jester, which consistently verify effectiveness of our approach, and demonstrate that our method can achieve higher performance than state-of-the-art methods with the same backbone.

preprint2020arXiv

Conditional Sequential Modulation for Efficient Global Image Retouching

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of $1\times1$ convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://github.com/hejingwenhejingwen/CSRNet.

preprint2020arXiv

Enhanced Quadratic Video Interpolation

With the prosperity of digital video industry, video frame interpolation has arisen continuous attention in computer vision community and become a new upsurge in industry. Many learning-based methods have been proposed and achieved progressive results. Among them, a recent algorithm named quadratic video interpolation (QVI) achieves appealing performance. It exploits higher-order motion information (e.g. acceleration) and successfully models the estimation of interpolated flow. However, its produced intermediate frames still contain some unsatisfactory ghosting, artifacts and inaccurate motion, especially when large and complex motion occurs. In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model. In particular, we adopt a rectified quadratic flow prediction (RQFP) formulation with least squares method to estimate the motion more accurately. Complementary with image pixel-level blending, we introduce a residual contextual synthesis network (RCSN) to employ contextual information in high-dimensional feature space, which could help the model handle more complicated scenes and motion patterns. Moreover, to further boost the performance, we devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process. The proposed EQVI model won the first place in the AIM2020 Video Temporal Super-Resolution Challenge.

preprint2020arXiv

Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution

Multi-scale techniques have achieved great success in a wide range of computer vision tasks. However, while this technique is incorporated in existing works, there still lacks a comprehensive investigation on variants of multi-scale convolution in image super resolution. In this work, we present a unified formulation over widely-used multi-scale structures. With this framework, we systematically explore the two factors of multi-scale convolution -- feature propagation and cross-scale communication. Based on the investigation, we propose a generic and efficient multi-scale convolution unit -- Multi-Scale cross-Scale Share-weights convolution (MS$^3$-Conv). Extensive experiments demonstrate that the proposed MS$^3$-Conv can achieve better SR performance than the standard convolution with less parameters and computational cost. Beyond quantitative analysis, we comprehensively study the visual quality, which shows that MS$^3$-Conv behave better to recover high-frequency details.

preprint2020arXiv

Flow electrification of corona-charged polyethylene terephthalate film

Corona charging a free-standing polymer film can produce a quasi-permanent potential difference across the film thickness, while the absolute amplitude of surface voltage may be highly sensitive to the free charges. To precisely control the voltage distribution, we investigated the flow electrification technology, by exposing corona-charged polyethylene terephthalate films to a variety of sodium salt solutions. The surface voltage and the free charge density were adjusted by the salt concentration, the anion size, and the flow rate. The dipolar component of electric potential remained unchanged. This result has significant scientific interest and technological importance to surface treatment, filtration, energy harvesting, bio-actuation and bio-sensing, among others.

preprint2020arXiv

Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

Interactive image restoration aims to generate restored images by adjusting a controlling coefficient which determines the restoration level. Previous works are restricted in modulating image with a single coefficient. However, real images always contain multiple types of degradation, which cannot be well determined by one coefficient. To make a step forward, this paper presents a new problem setup, called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels. Compared with the previous single-dimension (SD) modulation, the MD is setup to handle multiple degradations adaptively and relief unbalanced learning problem in different degradations. We also propose a deep architecture - CResMD with newly introduced controllable residual connections for multi-dimension modulation. Specifically, we add a controlling variable on the conventional residual connection to allow a weighted summation of input and residual. The values of these weights are generated by another condition network. We further propose a new data sampling strategy based on beta distribution to balance different degradation types and levels. With corrupted image and degradation information as inputs, the network can output the corresponding restored image. By tweaking the condition vector, users can control the output effects in MD space at test time. Extensive experiments demonstrate that the proposed CResMD achieve excellent performance on both SD and MD modulation tasks. Code is available at https://github.com/hejingwenhejingwen/CResMD.

preprint2020arXiv

Learning Attentive Pairwise Interaction for Fine-Grained Classification

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft(93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%).

preprint2020arXiv

Learning to Predict Context-adaptive Convolution for Semantic Segmentation

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K.

preprint2020arXiv

Pose-Assisted Multi-Camera Collaboration for Active Object Tracking

Active Object Tracking (AOT) is crucial to many visionbased applications, e.g., mobile robot, intelligent surveillance. However, there are a number of challenges when deploying active tracking in complex scenarios, e.g., target is frequently occluded by obstacles. In this paper, we extend the single-camera AOT to a multi-camera setting, where cameras tracking a target in a collaborative fashion. To achieve effective collaboration among cameras, we propose a novel Pose-Assisted Multi-Camera Collaboration System, which enables a camera to cooperate with the others by sharing camera poses for active object tracking. In the system, each camera is equipped with two controllers and a switcher: The vision-based controller tracks targets based on observed images. The pose-based controller moves the camera in accordance to the poses of the other cameras. At each step, the switcher decides which action to take from the two controllers according to the visibility of the target. The experimental results demonstrate that our system outperforms all the baselines and is capable of generalizing to unseen environments. The code and demo videos are available on our website https://sites.google.com/view/pose-assistedcollaboration.

preprint2020arXiv

Progressive Object Transfer Detection

Recent development of object detection mainly depends on deep learning with large-scale benchmarks. However, collecting such fully-annotated data is often difficult or expensive for real-world applications, which restricts the power of deep neural networks in practice. Alternatively, humans can detect new objects with little annotation burden, since humans often use the prior knowledge to identify new objects with few elaborately-annotated examples, and subsequently generalize this capacity by exploiting objects from wild images. Inspired by this procedure of learning to detect, we propose a novel Progressive Object Transfer Detection (POTD) framework. Specifically, we make three main contributions in this paper. First, POTD can leverage various object supervision of different domains effectively into a progressive detection procedure. Via such human-like learning, one can boost a target detection task with few annotations. Second, POTD consists of two delicate transfer stages, i.e., Low-Shot Transfer Detection (LSTD), and Weakly-Supervised Transfer Detection (WSTD). In LSTD, we distill the implicit object knowledge of source detector to enhance target detector with few annotations. It can effectively warm up WSTD later on. In WSTD, we design a recurrent object labelling mechanism for learning to annotate weakly-labeled images. More importantly, we exploit the reliable object supervision from LSTD, which can further enhance the robustness of target detector in the WSTD stage. Finally, we perform extensive experiments on a number of challenging detection benchmarks with different settings. The results demonstrate that, our POTD outperforms the recent state-of-the-art approaches.

preprint2020arXiv

Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the vanilla gates in RNN (e.g., the input gate in LSTM) suffer from the problem of gate undertraining, which can be caused by various factors, such as the saturating activation functions, the gate layouts (e.g., the gate number and gating functions), or even the suboptimal memory state etc.. Those may result in failures of learning gating switch roles and thus the weak performance. In this paper, we propose a new gating mechanism within general gated recurrent neural networks to handle this issue. Specifically, the proposed gates directly short connect the extracted input features to the outputs of vanilla gates, denoted as refined gates. The refining mechanism allows enhancing gradient back-propagation as well as extending the gating activation scope, which can guide RNN to reach possibly deeper minima. We verify the proposed gating mechanism on three popular types of gated RNNs including LSTM, GRU and MGU. Extensive experiments on 3 synthetic tasks, 3 language modeling tasks and 5 scene text recognition benchmarks demonstrate the effectiveness of our method.

preprint2020arXiv

Sand-Filler Structural Material with Low Content of Polyethylene Binder

Currently, most of the waste plastics cannot be recycled, causing serious environmental concerns. In this research, we investigated a compaction formation technology to fabricate structural materials with thermoplastic binders. When the compaction pressure was 70~100 MPa, with only ~10 wt% polyethylene binder, the flexural strength was greater than that of typical steel-reinforced concrete, suitable to many construction applications. Because construction materials are tolerant to impurities, our work may provide a promising opportunity to recycle waste plastics and to reduce the portland cement production.

preprint2020arXiv

SmallBigNet: Integrating Core and Contextual Views for Video Classification

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://github.com/xhl-video/SmallBigNet.

preprint2020arXiv

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators. These uncertainties lead to a key challenge of large-scale Facial Expression Recognition (FER) in deep learning era. To address this problem, this paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial images. Specifically, SCN suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over mini-batch to weight each training sample with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group. Experiments on synthetic FER datasets and our collected WebEmotion dataset validate the effectiveness of our method. Results on public benchmarks demonstrate that our SCN outperforms current state-of-the-art methods with \textbf{88.14}\% on RAF-DB, \textbf{60.23}\% on AffectNet, and \textbf{89.35}\% on FERPlus. The code will be available at \href{https://github.com/kaiwang960112/Self-Cure-Network}{https://github.com/kaiwang960112/Self-Cure-Network}.

preprint2020arXiv

Thermal Insulating Polymer-Air Multilayer for Window Energy Efficiency

Polymer-air multilayer (PAM) was developed to decrease the heat loss through window glass panes. A PAM consists of a few polymer films separated from each other by air gaps. Thanks to the excellent optical properties of the polymer films, the visual transmittance of PAM is higher than 70%, and the haze is less than 2%. PAM not only has mechanisms to reduce the conductive and convective heat transfer, but also can obstruct the radiative heat transfer. With a 4~6 mm thick PAM coating, the U-factor of a glass pane can be lowered from above 1 Btu/{{h}{ft}^2{°F}} to 0.5~0.6 Btu/{{h}{ft}^2{°F}} .PAM is resilient and robust, relevant to the window retrofitting applications.

preprint2020arXiv

TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient.

Yu Qiao

Quick read

Decide how to stay connected

How to connect with this researcher

Open a focused conversation when the fit is right

See the researcher in context

Building this graph slice

61 published item(s)

StableI2I: Spotting Unintended Changes in Image-to-Image Transition

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning

InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

VideoChat: Chat-Centric Video Understanding

Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields

On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

Blueprint Separable Residual Network for Efficient Image Super-Resolution

Cohomology and deformations of Relative Rota-Baxter operators on Lie-Yamaguti algebras

ConvMAE: Masked Convolution Meets Masked Autoencoders

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

Discovering Distinctive &#34;Semantics&#34; in Super-Resolution Networks

Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning

Domain Generalization: A Survey

Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition

Frozen CLIP Models are Efficient Video Learners

GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation

HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints

INTERN: A New Learning Paradigm Towards General Vision

Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot

Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns

MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

POS-BERT: Point Cloud One-Stage BERT Pre-Training

Producing Useful Work in a Cycle by Absorbing Heat from a Single Thermal Reservoir: An Investigation on a Locally Nonchaotic Energy Barrier

Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features

Reflash Dropout in Image Super-Resolution

Self-slimmed Vision Transformer

Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification

UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning

Very Lightweight Photo Retouching Network with Conditional Sequential Modulation

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

Affordance Transfer Learning for Human-Object Interaction Detection

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation

ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

Multi-scale Information Assembly for Image Matting

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering

A Comprehensive Study on Temporal Modeling for Online Action Detection

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

Algae-Filler Artificial Timber with an Ultralow Binder Content

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification

Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition

Conditional Sequential Modulation for Efficient Global Image Retouching

Enhanced Quadratic Video Interpolation

Exploring Multi-Scale Feature Propagation and Communication for Image Super Resolution

Flow electrification of corona-charged polyethylene terephthalate film

Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

Learning Attentive Pairwise Interaction for Fine-Grained Classification

Learning to Predict Context-adaptive Convolution for Semantic Segmentation

Pose-Assisted Multi-Camera Collaboration for Active Object Tracking

Progressive Object Transfer Detection

Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units

Sand-Filler Structural Material with Low Content of Polyethylene Binder

SmallBigNet: Integrating Core and Contextual Views for Video Classification

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Thermal Insulating Polymer-Air Multilayer for Window Energy Efficiency

TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation

Discovering Distinctive "Semantics" in Super-Resolution Networks