BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Rui Zhao

Rui Zhao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningArtificial IntelligenceComputation and Languageeess.ASSoundeess.SPDistributed, Parallel, and Cluster Computingeess.IVeess.SYInformation RetrievalMultimediaphysics.opticsRoboticsSystems and Control

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
34works
0followers
15topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

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

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

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.

Published work

34 published item(s)

preprint2026arXiv

End-to-end autonomous scientific discovery on a real optical platform

Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (LLM)-based agents are beginning to move beyond assisting predefined research workflows, none has yet demonstrated end-to-end autonomous discovery in a real physical system that produces a nontrivial result supported by experimental evidence. Here we introduce Qiushi Discovery Engine, an LLM-based agentic system for end-to-end autonomous scientific discovery on a real optical platform. Qiushi Engine combines nonlinear research phases, Meta-Trace memory and a dual-layer architecture to maintain adaptive and stable research trajectories across long-horizon investigations involving thousands of LLM-mediated reasoning, measurement and revision actions. It autonomously reproduces a published transmission-matrix experiment on a non-original platform and converts an abstract coherence-order theory into experimental observables, providing, to our knowledge, the first observation of this class of coherence-order structure. More importantly, in an open-ended study involving 145.9 million tokens, 3,242 LLM calls, 1,242 tool calls, 163 research notes and 44 scripts, Qiushi Engine proposes and experimentally validates optical bilinear interaction, a physical mechanism structurally analogous to a core operation in Transformer attention. This AI-discovered mechanism suggests a route towards high-speed, energy-efficient optical hardware for pairwise computation. To our knowledge, this is the first demonstration of an AI agentic system autonomously identifying and experimentally validating a nontrivial, previously unreported physical mechanism, marking a milestone for research-level autonomous agents.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Transformer in Transformer as Backbone for Deep Reinforcement Learning

Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work focuses on the former. Previous methods build the network with several modules like CNN, LSTM and Attention. Recent methods combine the Transformer with these modules for better performance. However, it requires tedious optimization skills to train a network composed of mixed modules, making these methods inconvenient to be used in practice. In this paper, we propose to design \emph{pure Transformer-based networks} for deep RL, aiming at providing off-the-shelf backbones for both the online and offline settings. Specifically, the Transformer in Transformer (TIT) backbone is proposed, which cascades two Transformers in a very natural way: the inner one is used to process a single observation, while the outer one is responsible for processing the observation history; combining both is expected to extract spatial-temporal representations for good decision-making. Experiments show that TIT can achieve satisfactory performance in different settings consistently.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain. Therefore, the self-supervised learning from multiple domains task is proposed to learn domain-invariant features that are not only suitable for evaluation on the same domain as the training set but also can be generalized to unseen domains. In this paper, we propose a Domain-invariant Masked AutoEncoder (DiMAE) for self-supervised learning from multi-domains, which designs a new pretext task, \emph{i.e.,} the cross-domain reconstruction task, to learn domain-invariant features. The core idea is to augment the input image with style noise from different domains and then reconstruct the image from the embedding of the augmented image, regularizing the encoder to learn domain-invariant features. To accomplish the idea, DiMAE contains two critical designs, 1) content-preserved style mix, which adds style information from other domains to input while persevering the content in a parameter-free manner, and 2) multiple domain-specific decoders, which recovers the corresponding domain style of input to the encoded domain-invariant features for reconstruction. Experiments on PACS and DomainNet illustrate that DiMAE achieves considerable gains compared with recent state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DOTIN: Dropping Task-Irrelevant Nodes for GNNs

Scalability is an important consideration for deep graph neural networks. Inspired by the conventional pooling layers in CNNs, many recent graph learning approaches have introduced the pooling strategy to reduce the size of graphs for learning, such that the scalability and efficiency can be improved. However, these pooling-based methods are mainly tailored to a single graph-level task and pay more attention to local information, limiting their performance in multi-task settings which often require task-specific global information. In this paper, departure from these pooling-based efforts, we design a new approach called DOTIN (\underline{D}r\underline{o}pping \underline{T}ask-\underline{I}rrelevant \underline{N}odes) to reduce the size of graphs. Specifically, by introducing $K$ learnable virtual nodes to represent the graph embeddings targeted to $K$ different graph-level tasks, respectively, up to 90\% raw nodes with low attentiveness with an attention model -- a transformer in this paper, can be adaptively dropped without notable performance decreasing. Achieving almost the same accuracy, our method speeds up GAT by about 50\% on graph-level tasks including graph classification and graph edit distance (GED) with about 60\% less memory, on D\&D dataset. Code will be made publicly available in https://github.com/Sherrylone/DOTIN.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Feature Erasing and Diffusion Network for Occluded Person Re-Identification

Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are usually disturbed by Non-Pedestrian Occlusions (NPO) and NonTarget Pedestrians (NTP). Previous methods mainly focus on increasing model's robustness against NPO while ignoring feature contamination from NTP. In this paper, we propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle NPO and NTP. Specifically, NPO features are eliminated by our proposed Occlusion Erasing Module (OEM), aided by the NPO augmentation strategy which simulates NPO on holistic pedestrian images and generates precise occlusion masks. Subsequently, we Subsequently, we diffuse the pedestrian representations with other memorized features to synthesize NTP characteristics in the feature space which is achieved by a novel Feature Diffusion Module (FDM) through a learnable cross attention mechanism. With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics. By jointly optimizing OEM and FDM in our proposed FED network, we can greatly improve the model's perception ability towards TP and alleviate the influence of NPO and NTP. Furthermore, the proposed FDM only works as an auxiliary module for training and will be discarded in the inference phase, thus introducing little inference computational overhead. Experiments on occluded and holistic person ReID benchmarks demonstrate the superiority of FED over state-of-the-arts, where FED achieves 86.3% Rank-1 accuracy on Occluded-REID, surpassing others by at least 4.7%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization

The essence of unsupervised anomaly detection is to learn the compact distribution of normal samples and detect outliers as anomalies in testing. Meanwhile, the anomalies in real-world are usually subtle and fine-grained in a high-resolution image especially for industrial applications. Towards this end, we propose a novel framework for unsupervised anomaly detection and localization. Our method aims at learning dense and compact distribution from normal images with a coarse-to-fine alignment process. The coarse alignment stage standardizes the pixel-wise position of objects in both image and feature levels. The fine alignment stage then densely maximizes the similarity of features among all corresponding locations in a batch. To facilitate the learning with only normal images, we propose a new pretext task called non-contrastive learning for the fine alignment stage. Non-contrastive learning extracts robust and discriminating normal image representations without making assumptions on abnormal samples, and it thus empowers our model to generalize to various anomalous scenarios. Extensive experiments on two typical industrial datasets of MVTec AD and BenTech AD demonstrate that our framework is effective in detecting various real-world defects and achieves a new state-of-the-art in industrial unsupervised anomaly detection.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination

We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through self-play training, they can suffer significantly from distributional shift when paired with unencountered partners, such as humans. To mitigate this distributional shift, we propose Maximum Entropy Population-based training (MEP). In MEP, agents in the population are trained with our derived Population Entropy bonus to promote both pairwise diversity between agents and individual diversity of agents themselves, and a common best agent is trained by paring with agents in this diversified population via prioritized sampling. The prioritization is dynamically adjusted based on the training progress. We demonstrate the effectiveness of our method MEP, with comparison to Self-Play PPO (SP), Population-Based Training (PBT), Trajectory Diversity (TrajeDi), and Fictitious Co-Play (FCP) in the Overcooked game environment, with partners being human proxy models and real humans. A supplementary video showing experimental results is available at https://youtu.be/Xh-FKD0AAKE.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Optical Flow Estimation for Spiking Camera

As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based methods are not well suited to spike streams from the spiking camera due to the different data modalities. To this end, we present, SCFlow, a tailored deep learning pipeline to estimate optical flow in high-speed scenes from spike streams. Importantly, a novel input representation is introduced which can adaptively remove the motion blur in spike streams according to the prior motion. Further, for training SCFlow, we synthesize two sets of optical flow data for the spiking camera, SPIkingly Flying Things and Photo-realistic High-speed Motion, denoted as SPIFT and PHM respectively, corresponding to random high-speed and well-designed scenes. Experimental results show that the SCFlow can predict optical flow from spike streams in different high-speed scenes. Moreover, SCFlow shows promising generalization on \textbf{real spike streams}. Codes and datasets refer to https://github.com/Acnext/Optical-Flow-For-Spiking-Camera.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Revisiting the Transferability of Supervised Pretraining: an MLP Perspective

The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervised counterparts. This paper revisits this phenomenon and sheds new light on understanding the transferability gap between unsupervised and supervised pretraining from a multilayer perceptron (MLP) perspective. While previous works focus on the effectiveness of MLP on unsupervised image classification where pretraining and evaluation are conducted on the same dataset, we reveal that the MLP projector is also the key factor to better transferability of unsupervised pretraining methods than supervised pretraining methods. Based on this observation, we attempt to close the transferability gap between supervised and unsupervised pretraining by adding an MLP projector before the classifier in supervised pretraining. Our analysis indicates that the MLP projector can help retain intra-class variation of visual features, decrease the feature distribution distance between pretraining and evaluation datasets, and reduce feature redundancy. Extensive experiments on public benchmarks demonstrate that the added MLP projector significantly boosts the transferability of supervised pretraining, e.g. +7.2% top-1 accuracy on the concept generalization task, +5.8% top-1 accuracy for linear evaluation on 12-domain classification tasks, and +0.8% AP on COCO object detection task, making supervised pretraining comparable or even better than unsupervised pretraining.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

The crux of semi-supervised semantic segmentation is to assign adequate pseudo-labels to the pixels of unlabeled images. A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability. We argue that every pixel matters to the model training, even its prediction is ambiguous. Intuitively, an unreliable prediction may get confused among the top classes (i.e., those with the highest probabilities), however, it should be confident about the pixel not belonging to the remaining classes. Hence, such a pixel can be convincingly treated as a negative sample to those most unlikely categories. Based on this insight, we develop an effective pipeline to make sufficient use of unlabeled data. Concretely, we separate reliable and unreliable pixels via the entropy of predictions, push each unreliable pixel to a category-wise queue that consists of negative samples, and manage to train the model with all candidate pixels. Considering the training evolution, where the prediction becomes more and more accurate, we adaptively adjust the threshold for the reliable-unreliable partition. Experimental results on various benchmarks and training settings demonstrate the superiority of our approach over the state-of-the-art alternatives.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Spatio-Temporal Recurrent Networks for Event-Based Optical Flow Estimation

Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing promising solutions to many event-based problems, such as optical flow estimation. However, existing deep learning methods did not address the importance of temporal information well from the perspective of architecture design and cannot effectively extract spatio-temporal features. Another line of research that utilizes Spiking Neural Network suffers from training issues for deeper architecture.To address these points, a novel input representation is proposed that captures the events' temporal distribution for signal enhancement. Moreover, we introduce a spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images. Besides, our architecture allows some traditional frame-based core modules, such as correlation layer and iterative residual refine scheme, to be incorporated. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin. The code link is https://github.com/ruizhao26/STE-FlowNet.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID

Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to an unlabeled target-domain dataset. The task of UDA on open-set person re-identification (re-ID) is even more challenging as the identities (classes) do not have overlap between the two domains. One major research direction was based on domain translation, which, however, has fallen out of favor in recent years due to inferior performance compared to pseudo-label-based methods. We argue that the domain translation has great potential on exploiting the valuable source-domain data but existing methods did not provide proper regularization on the translation process. Specifically, previous methods only focus on maintaining the identities of the translated images while ignoring the inter-sample relations during translation. To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term. During training, the person feature encoder is optimized to model inter-sample relations on-the-fly for supervising relation-consistency domain translation, which in turn, improves the encoder with informative translated images. The encoder can be further improved with pseudo labels, where the source-to-target translated images with ground-truth identities and target-domain images with pseudo identities are jointly used for training. In the experiments, our proposed framework is shown to achieve state-of-the-art performance on multiple UDA tasks of person re-ID. With the synthetic-to-real translated images from our structured domain-translation network, we achieved second place in the Visual Domain Adaptation Challenge (VisDA) in 2020.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation

As RGB-D sensors become more affordable, using RGB-D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use different backbones to extract features for RGB and depth images. They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion. We find that the essential reason for using two independent backbones is the "projection breakdown" problem. In the depth image plane, the projected 3D structure of the physical world is preserved by the 1D depth value and its built-in 2D pixel coordinate (UV). Any spatial transformation that modifies UV, such as resize, flip, crop, or pooling operations in the CNN pipeline, breaks the binding between the pixel value and UV coordinate. As a consequence, the 3D structure is no longer preserved by a modified depth image or feature. To address this issue, we propose a simple yet effective method denoted as Uni6D that explicitly takes the extra UV data along with RGB-D images as input. Our method has a Unified CNN framework for 6D pose estimation with a single CNN backbone. In particular, the architecture of our method is based on Mask R-CNN with two extra heads, one named RT head for directly predicting 6D pose and the other named abc head for guiding the network to map the visible points to their coordinates in the 3D model as an auxiliary module. This end-to-end approach balances simplicity and accuracy, achieving comparable accuracy with state of the arts and 7.2x faster inference speed on the YCB-Video dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

UniVIP: A Unified Framework for Self-Supervised Visual Pre-training

Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the scene and instances, as well as the semantic difference of instances in the scene. To address the above problems, we propose a Unified Self-supervised Visual Pre-training (UniVIP), a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. The framework takes into account the representation learning at three levels: 1) the similarity of scene-scene, 2) the correlation of scene-instance, 3) the discrimination of instance-instance. During the learning, we adopt the optimal transport algorithm to automatically measure the discrimination of instances. Massive experiments show that UniVIP pre-trained on non-iconic COCO achieves state-of-the-art transfer performance on a variety of downstream tasks, such as image classification, semi-supervised learning, object detection and segmentation. Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2.5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.

0 citations0 reviewsNo code linkedOpen access
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.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Continual Representation Learning for Biometric Identification

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning (CL) setting, namely ``continual representation learning'', which focuses on learning better representation in a continuous way. We also provide two large-scale multi-step benchmarks for biometric identification, where the visual appearance of different classes are highly relevant. In contrast to requiring the model to recognize more learned classes, we aim to learn feature representation that can be better generalized to not only previously unseen images but also unseen classes/identities. For the new setting, we propose a novel approach that performs the knowledge distillation over a large number of identities by applying the neighbourhood selection and consistency relaxation strategies to improve scalability and flexibility of the continual learning model. We demonstrate that existing CL methods can improve the representation in the new setting, and our method achieves better results than the competitors.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Curiosity-Driven Experience Prioritization via Density Estimation

In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states. The problem of learning from imbalanced data is a well-known problem in supervised learning, but has not yet been thoroughly researched in RL. To address this problem, we propose a novel Curiosity-Driven Prioritization (CDP) framework to encourage the agent to over-sample those trajectories that have rare achieved goal states. The CDP framework mimics the human learning process and focuses more on relatively uncommon events. We evaluate our methods using the robotic environment provided by OpenAI Gym. The environment contains six robot manipulation tasks. In our experiments, we combined CDP with Deep Deterministic Policy Gradient (DDPG) with or without Hindsight Experience Replay (HER). The experimental results show that CDP improves both performance and sample-efficiency of reinforcement learning agents, compared to state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Reinforcement Learning Based Mobile Edge Computing for Intelligent Internet of Things

In this paper, we investigate mobile edge computing (MEC) networks for intelligent internet of things (IoT), where multiple users have some computational tasks assisted by multiple computational access points (CAPs). By offloading some tasks to the CAPs, the system performance can be improved through reducing the latency and energy consumption, which are the two important metrics of interest in the MEC networks. We devise the system by proposing the offloading strategy intelligently through the deep reinforcement learning algorithm. In this algorithm, Deep Q-Network is used to automatically learn the offloading decision in order to optimize the system performance, and a neural network (NN) is trained to predict the offloading action, where the training data is generated from the environmental system. Moreover, we employ the bandwidth allocation in order to optimize the wireless spectrum for the links between the users and CAPs, where several bandwidth allocation schemes are proposed. In further, we use the CAP selection in order to choose one best CAP to assist the computational tasks from the users. Simulation results are finally presented to show the effectiveness of the proposed reinforcement learning offloading strategy. In particular, the system cost of latency and energy consumption can be reduced significantly by the proposed deep reinforcement learning based algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. In this paper, we describe our recent development of RNN-T models with reduced GPU memory consumption during training, better initialization strategy, and advanced encoder modeling with future lookahead. When trained with Microsoft's 65 thousand hours of anonymized training data, the developed RNN-T model surpasses a very well trained hybrid model with both better recognition accuracy and lower latency. We further study how to customize RNN-T models to a new domain, which is important for deploying E2E models to practical scenarios. By comparing several methods leveraging text-only data in the new domain, we found that updating RNN-T's prediction and joint networks using text-to-speech generated from domain-specific text is the most effective.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Efficient Dialog Policy Learning via Positive Memory Retention

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the collection of the required data in form of conversations between chat-bots and human agents is time-consuming and expensive. To mitigate this problem, we describe an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency. We show that our method is 10 times more sample-efficient than policy gradients in extensive experiments on a new synthetic number guessing game. Moreover, in a real-word visual object discovery game, the proposed method is twice as sample-efficient as policy gradients and shows state-of-the-art performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Energy-Based Hindsight Experience Prioritization

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based framework for prioritizing hindsight experience in robotic manipulation tasks. Our approach is inspired by the work-energy principle in physics. We define a trajectory energy function as the sum of the transition energy of the target object over the trajectory. We hypothesize that replaying episodes that have high trajectory energy is more effective for reinforcement learning in robotics. To verify our hypothesis, we designed a framework for hindsight experience prioritization based on the trajectory energy of goal states. The trajectory energy function takes the potential, kinetic, and rotational energy into consideration. We evaluate our Energy-Based Prioritization (EBP) approach on four challenging robotic manipulation tasks in simulation. Our empirical results show that our proposed method surpasses state-of-the-art approaches in terms of both performance and sample-efficiency on all four tasks, without increasing computational time. A video showing experimental results is available at https://youtu.be/jtsF2tTeUGQ

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis

Convolutional neural network (CNN)-based image denoising methods have been widely studied recently, because of their high-speed processing capability and good visual quality. However, most of the existing CNN-based denoisers learn the image prior from the spatial domain, and suffer from the problem of spatially variant noise, which limits their performance in real-world image denoising tasks. In this paper, we propose a discrete wavelet denoising CNN (WDnCNN), which restores images corrupted by various noise with a single model. Since most of the content or energy of natural images resides in the low-frequency spectrum, their transformed coefficients in the frequency domain are highly imbalanced. To address this issue, we present a band normalization module (BNM) to normalize the coefficients from different parts of the frequency spectrum. Moreover, we employ a band discriminative training (BDT) criterion to enhance the model regression. We evaluate the proposed WDnCNN, and compare it with other state-of-the-art denoisers. Experimental results show that WDnCNN achieves promising performance in both synthetic and real noise reduction, making it a potential solution to many practical image denoising applications.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However, RNN-T training is made difficult by the huge memory requirements, and complicated neural structure. A common solution to ease the RNN-T training is to employ connectionist temporal classification (CTC) model along with RNN language model (RNNLM) to initialize the RNN-T parameters. In this work, we conversely leverage external alignments to seed the RNN-T model. Two different pre-training solutions are explored, referred to as encoder pre-training, and whole-network pre-training respectively. Evaluated on Microsoft 65,000 hours anonymized production data with personally identifiable information removed, our proposed methods can obtain significant improvement. In particular, the encoder pre-training solution achieved a 10% and a 8% relative word error rate reduction when compared with random initialization and the widely used CTC+RNNLM initialization strategy, respectively. Our solutions also significantly reduce the RNN-T model latency from the baseline.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Harvest-and-Opportunistically-Relay: Analyses on Transmission Outage and Covertness

For enhancing transmission performance, privacy level and energy manipulating efficiency of wireless networks, this paper initiates a novel simultaneous wireless information and power transfer (SWIPT) full-duplex (FD) relaying protocol, termed harvest-and-opportunistically-relay (HOR). In the proposed HOR protocol, the relay can work opportunistically in either pure energy harvesting (PEH) or the FD SWIPT mode. Due to the FD characteristics, the dynamic fluctuation of R's residual energy is difficult to quantify and track. To solve this problem, we apply a novel discrete-state Markov Chain (MC) method in which the practical finite-capacity energy storage is considered. Furthermore, to improve the privacy level of the proposed HOR relaying system, covert transmission performance analysis is developed and investigated, where closed-form expressions of optimal detection threshold and minimum detection error probability are derived. Last but not least, with the aid of stationary distribution of the MC, closed-form expression of transmission outage probability is calculated, based on which transmission outage performance is analyzed. Numerical results have validated the correctness of analyses on transmission outage and covert communication. The impacts of key system parameters on the performance of transmission outage and covert communication are given and discussed. Based on mathematical analysis and numerical results, it is fair to say that the proposed HOR model is able to not only reliably enhance the transmission performance via smartly managing residual energy but also efficiently improve the privacy level of the legitimate transmission party via dynamically adjust the optimal detection threshold.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that such conventional hybrid models can still be significantly improved. In this paper, we detail our recent efforts to improve conventional hybrid LSTM acoustic models for high-accuracy and low-latency automatic speech recognition. To achieve high accuracy, we use a contextual layer trajectory LSTM (cltLSTM), which decouples the temporal modeling and target classification tasks, and incorporates future context frames to get more information for accurate acoustic modeling. We further improve the training strategy with sequence-level teacher-student learning. To obtain low latency, we design a two-head cltLSTM, in which one head has zero latency and the other head has a small latency, compared to an LSTM. When trained with Microsoft's 65 thousand hours of anonymized training data and evaluated with test sets with 1.8 million words, the proposed two-head cltLSTM model with the proposed training strategy yields a 28.2\% relative WER reduction over the conventional LSTM acoustic model, with a similar perceived latency.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient

Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and Memory Network structures that leads to an improvement of 7%. The second one is the application of our newly developed TPG methods, which improves the performance additionally by around 5% and, even more importantly, helps produce more convincing utterances.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning to Cluster Faces via Confidence and Connectivity Estimation

Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance gain. However, they usually involve heuristic steps and require numerous overlapped subgraphs, severely restricting their accuracy and efficiency. In this paper, we propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs. Instead, we transform the clustering problem into two sub-problems. Specifically, two graph convolutional networks, named GCN-V and GCN-E, are designed to estimate the confidence of vertices and the connectivity of edges, respectively. With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters. Experiments on two large-scale benchmarks show that our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Maximum Entropy-Regularized Multi-Goal Reinforcement Learning

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biased towards the behavior policies. From a Bayesian perspective, when there is no prior knowledge about the target goal distribution, the agent should learn uniformly from diverse achieved goals. Therefore, we first propose a novel multi-goal RL objective based on weighted entropy. This objective encourages the agent to maximize the expected return, as well as to achieve more diverse goals. Secondly, we developed a maximum entropy-based prioritization framework to optimize the proposed objective. For evaluation of this framework, we combine it with Deep Deterministic Policy Gradient, both with or without Hindsight Experience Replay. On a set of multi-goal robotic tasks of OpenAI Gym, we compare our method with other baselines and show promising improvements in both performance and sample-efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning

In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized efficiently. Lastly, we evaluate the developed framework in different robotic manipulation and navigation tasks and demonstrate the efficacy of our approach. A video showing experimental results is available at https://youtu.be/CT4CKMWBYz0

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition

Recently, there has been a strong push to transition from hybrid models to end-to-end (E2E) models for automatic speech recognition. Currently, there are three promising E2E methods: recurrent neural network transducer (RNN-T), RNN attention-based encoder-decoder (AED), and Transformer-AED. In this study, we conduct an empirical comparison of RNN-T, RNN-AED, and Transformer-AED models, in both non-streaming and streaming modes. We use 65 thousand hours of Microsoft anonymized training data to train these models. As E2E models are more data hungry, it is better to compare their effectiveness with large amount of training data. To the best of our knowledge, no such comprehensive study has been conducted yet. We show that although AED models are stronger than RNN-T in the non-streaming mode, RNN-T is very competitive in streaming mode if its encoder can be properly initialized. Among all three E2E models, transformer-AED achieved the best accuracy in both streaming and non-streaming mode. We show that both streaming RNN-T and transformer-AED models can obtain better accuracy than a highly-optimized hybrid model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Self-supervising Fine-grained Region Similarities for Large-scale Image Localization

The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potential of difficult positive images alongside their sub-regions. The estimated image-to-region similarities can serve as extra training supervision for improving the network in generations, which could in turn gradually refine the fine-grained similarities to achieve optimal performance. Our proposed self-enhanced image-to-region similarity labels effectively deal with the training bottleneck in the state-of-the-art pipelines without any additional parameters or manual annotations in both training and inference. Our method outperforms state-of-the-arts on the standard localization benchmarks by noticeable margins and shows excellent generalization capability on multiple image retrieval datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Stacked Convolutional Deep Encoding Network for Video-Text Retrieval

Existing dominant approaches for cross-modal video-text retrieval task are to learn a joint embedding space to measure the cross-modal similarity. However, these methods rarely explore long-range dependency inside video frames or textual words leading to insufficient textual and visual details. In this paper, we propose a stacked convolutional deep encoding network for video-text retrieval task, which considers to simultaneously encode long-range and short-range dependency in the videos and texts. Specifically, a multi-scale dilated convolutional (MSDC) block within our approach is able to encode short-range temporal cues between video frames or text words by adopting different scales of kernel size and dilation size of convolutional layer. A stacked structure is designed to expand the receptive fields by repeatedly adopting the MSDC block, which further captures the long-range relations between these cues. Moreover, to obtain more robust textual representations, we fully utilize the powerful language model named Transformer in two stages: pretraining phrase and fine-tuning phrase. Extensive experiments on two different benchmark datasets (MSR-VTT, MSVD) show that our proposed method outperforms other state-of-the-art approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Transfer Learning Approaches for Streaming End-to-End Speech Recognition System

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural network transducer (RNN-T) models, by initializing the encoder and/or prediction network of the target language with the pre-trained models from source language. In the hybrid ASR system, transfer learning is typically done by initializing the target language acoustic model (AM) with source language AM. Several transfer learning strategies exist in the case of the RNN-T framework, depending upon the choice of the initialization model for encoder and prediction networks. This paper presents a comparative study of four different TL methods for RNN-T framework. We show 17% relative word error rate reduction with different TL methods over randomly initialized RNN-T model. We also study the impact of TL with varying amount of training data ranging from 50 hours to 1000 hours and show the efficacy of TL for languages with small amount of training data.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Woodpecker-DL: Accelerating Deep Neural Networks via Hardware-Aware Multifaceted Optimizations

Accelerating deep model training and inference is crucial in practice. Existing deep learning frameworks usually concentrate on optimizing training speed and pay fewer attentions to inference-specific optimizations. Actually, model inference differs from training in terms of computation, e.g. parameters are refreshed each gradient update step during training, but kept invariant during inference. These special characteristics of model inference open new opportunities for its optimization. In this paper, we propose a hardware-aware optimization framework, namely Woodpecker-DL (WPK), to accelerate inference by taking advantage of multiple joint optimizations from the perspectives of graph optimization, automated searches, domain-specific language (DSL) compiler techniques and system-level exploration. In WPK, we investigated two new automated search approaches based on genetic algorithm and reinforcement learning, respectively, to hunt the best operator code configurations targeting specific hardware. A customized DSL compiler is further attached to these search algorithms to generate efficient codes. To create an optimized inference plan, WPK systematically explores high-speed operator implementations from third-party libraries besides our automatically generated codes and singles out the best implementation per operator for use. Extensive experiments demonstrated that on a Tesla P100 GPU, we can achieve the maximum speedup of 5.40 over cuDNN and 1.63 over TVM on individual convolution operators, and run up to 1.18 times faster than TensorRT for end-to-end model inference.

0 citations0 reviewsNo code linkedOpen access