Search Results for author: Wei zhang

Found 279 papers, 75 papers with code

Unsupervised Multi-View CNN for Salient View Selection of 3D Objects and Scenes

1 code implementation ECCV 2020 Ran Song, Wei zhang, Yitian Zhao, Yonghuai Liu

We present an unsupervised 3D deep learning framework based on a ubiquitously true proposition named by us view-object consistency as it states that a 3D object and its projected 2D views always belong to the same object class.

HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity Prediction

no code implementations ECCV 2020 Tianjiao Li, Jun Liu, Wei zhang, Ling-Yu Duan

In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated.

Activity Prediction Skeleton Based Action Recognition

New volatility evolution model after extreme events

no code implementations10 Jan 2022 Mei-Ling Cai, Zhang-HangJian Chen, Sai-Ping Li, Xiong Xiong, Wei zhang, Ming-Yuan Yang, Fei Ren

Empirical study of the evolutionary behaviors of volatility after endogenous and exogenous events further demonstrates the descriptive power of our new model.

What Hinders Perceptual Quality of PSNR-oriented Methods?

no code implementations4 Jan 2022 Tianshuo Xu, Peng Mi, Xiawu Zheng, Lijiang Li, Fei Chao, Guannan Jiang, Wei zhang, Yiyi Zhou, Rongrong Ji

E. g, in EDSR, our proposed method achieves 3. 60$\times$ faster learning speed compared to a GAN-based method with a subtle degradation in visual quality.

Contrastive Learning

Data-Free Knowledge Transfer: A Survey

no code implementations31 Dec 2021 Yuang Liu, Wei zhang, Jun Wang, Jianyong Wang

In this paper, we provide a comprehensive survey on data-free knowledge transfer from the perspectives of knowledge distillation and unsupervised domain adaptation, to help readers have a better understanding of the current research status and ideas.

Knowledge Distillation Model Compression +2

Responsive Listening Head Generation: A Benchmark Dataset and Baseline

no code implementations27 Dec 2021 Mohan Zhou, Yalong Bai, Wei zhang, Tiejun Zhao, Tao Mei

We define the responsive listening head generation task as the synthesis of a non-verbal head with motions and expressions reacting to the multiple inputs, including the audio and visual signal of the speaker.

Talking Head Generation Translation

LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization

no code implementations10 Dec 2021 Zhiwei Chen, Changan Wang, Yabiao Wang, Guannan Jiang, Yunhang Shen, Ying Tai, Chengjie Wang, Wei zhang, Liujuan Cao

In this paper, we propose a novel framework built upon the transformer, termed LCTR (Local Continuity TRansformer), which targets at enhancing the local perception capability of global features among long-range feature dependencies.

Weakly-Supervised Object Localization

VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts

no code implementations4 Dec 2021 Renrui Zhang, Longtian Qiu, Wei zhang, Ziyao Zeng

Contrastive Vision-Language Pre-training (CLIP) has drown increasing attention recently for its transferable visual representation learning.

Language Modelling Representation Learning +1

PointCLIP: Point Cloud Understanding by CLIP

1 code implementation4 Dec 2021 Renrui Zhang, Ziyu Guo, Wei zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, Hongsheng Li

On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D.

Few-Shot Learning Transfer Learning

Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent

no code implementations2 Dec 2021 Wei zhang, Mingrui Liu, Yu Feng, Xiaodong Cui, Brian Kingsbury, Yuhai Tu

We conduct extensive studies over 18 state-of-the-art DL models/tasks and demonstrate that DPSGD often converges in cases where SSGD diverges for large learning rates in the large batch setting.

Speech Recognition

Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis

no code implementations2 Dec 2021 Zixuan Yuan, Yada Zhu, Wei zhang, Ziming Huang, Guangnan Ye, Hui Xiong

Earnings call (EC), as a periodic teleconference of a publicly-traded company, has been extensively studied as an essential market indicator because of its high analytical value in corporate fundamentals.

Data Augmentation

Optimizing for In-memory Deep Learning with Emerging Memory Technology

no code implementations1 Dec 2021 Zhehui Wang, Tao Luo, Rick Siow Mong Goh, Wei zhang, Weng-Fai Wong

In-memory deep learning has already demonstrated orders of magnitude higher performance density and energy efficiency.

Using Reconfigurable Intelligent Surfaces for UE Positioning in mmWave MIMO Systems

no code implementations1 Dec 2021 Wei zhang, Wee Peng Tay

We develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.

Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling

1 code implementation6 Nov 2021 Renrui Zhang, Rongyao Fang, Wei zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, Hongsheng Li

To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification.

Language Modelling Transfer Learning

Directional Self-supervised Learning for Heavy Image Augmentations

no code implementations26 Oct 2021 Yalong Bai, Yifan Yang, Wei zhang, Tao Mei

Specifically, we adapt heavy augmentation policies after the views lightly augmented by standard augmentations, to generate harder view (HV).

Representation Learning Self-Supervised Learning

ViDA-MAN: Visual Dialog with Digital Humans

no code implementations26 Oct 2021 Tong Shen, Jiawei Zuo, Fan Shi, Jin Zhang, Liqin Jiang, Meng Chen, Zhengchen Zhang, Wei zhang, Xiaodong He, Tao Mei

We demonstrate ViDA-MAN, a digital-human agent for multi-modal interaction, which offers realtime audio-visual responses to instant speech inquiries.

Speech Recognition Video Generation +1

IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

1 code implementation25 Oct 2021 Pan Lu, Liang Qiu, Jiaqi Chen, Tony Xia, Yizhou Zhao, Wei zhang, Zhou Yu, Xiaodan Liang, Song-Chun Zhu

Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset.

Object Recognition Question Answering +1

Asynchronous Decentralized Distributed Training of Acoustic Models

no code implementations21 Oct 2021 Xiaodong Cui, Wei zhang, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, David Kung

Specifically, we study three variants of asynchronous decentralized parallel SGD (ADPSGD), namely, fixed and randomized communication patterns on a ring as well as a delay-by-one scheme.

Speech Recognition

Sensoring and Application of Multimodal Data for the Detection of Freezing of Gait in Parkinson's Disease

no code implementations9 Oct 2021 Wei zhang, Debin Huang, Hantao Li, Lipeng Wang, Yanzhao Wei, Kang Pan, Lin Ma, Huanhuan Feng, Jing Pan, Yuzhu Guo

The accurate and reliable detection or prediction of freezing of gaits (FOG) is important for fall prevention in Parkinson's Disease (PD) and studying the physiological transitions during the occurrence of FOG.


TSK Fuzzy System Towards Few Labeled Incomplete Multi-View Data Classification

no code implementations8 Oct 2021 Wei zhang, Zhaohong Deng, Qiongdan Lou, Te Zhang, Kup-Sze Choi, Shitong Wang

The proposed method has the following distinctive characteristics: 1) it can deal with the incomplete and few labeled multi-view data simultaneously; 2) it integrates the missing view imputation and model learning as a single process, which is more efficient than the traditional two-step strategy; 3) attributed to the interpretable fuzzy inference rules, this method is more interpretable.


Scalable Rule-Based Representation Learning for Interpretable Classification

2 code implementations NeurIPS 2021 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.

Representation Learning

MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation

no code implementations25 Sep 2021 Zeyuan Chen, Jiangchao Yao, Feng Wang, Kunyang Jia, Bo Han, Wei zhang, Hongxia Yang

With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks.

Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation

1 code implementation24 Sep 2021 Zeyuan Chen, Wei zhang, Junchi Yan, Gang Wang, Jianyong Wang

Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items.

Representation Learning Sequential Recommendation

High-dimensional Bayesian Optimization for CNN Auto Pruning with Clustering and Rollback

no code implementations22 Sep 2021 Jiandong Mu, Hanwei Fan, Wei zhang

We validate our proposed method on ResNet, MobileNet, and VGG models, and our experiments show that the proposed method significantly improves the accuracy of BO when pruning very deep CNN models.

Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks

no code implementations21 Sep 2021 Chin-Chia Michael Yeh, Zhongfang Zhuang, Junpeng Wang, Yan Zheng, Javid Ebrahimi, Ryan Mercer, Liang Wang, Wei zhang

In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database.

Time Series Time Series Prediction

OMPQ: Orthogonal Mixed Precision Quantization

1 code implementation16 Sep 2021 Yuexiao Ma, Taisong Jin, Xiawu Zheng, Yan Wang, Huixia Li, Yongjian Wu, Yunsheng Wu, Guannan Jiang, Wei zhang, Rongrong Ji

Instead of solving a problem of the original integer programming, we propose to optimize a proxy metric, the concept of network orthogonality, which is highly correlated with the loss of the integer programming but also easy to optimize with linear programming.

AutoML Quantization

Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis

no code implementations5 Sep 2021 Tong Sha, Wei zhang, Tong Shen, Zhoujun Li, Tao Mei

Deep person generation has attracted extensive research attention due to its wide applications in virtual agents, video conferencing, online shopping and art/movie production.

Data Augmentation Talking Head Generation

How Does Adversarial Fine-Tuning Benefit BERT?

no code implementations31 Aug 2021 Javid Ebrahimi, Hao Yang, Wei zhang

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning.

Continual Learning Dependency Parsing +2

4-bit Quantization of LSTM-based Speech Recognition Models

no code implementations27 Aug 2021 Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Xiao Sun, Naigang Wang, Swagath Venkataramani, George Saon, Xiaodong Cui, Brian Kingsbury, Wei zhang, Zoltán Tüske, Kailash Gopalakrishnan

We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition (ASR): hybrid Deep Bidirectional LSTM - Hidden Markov Models (DBLSTM-HMMs) and Recurrent Neural Network - Transducers (RNN-Ts).

Quantization Speech Recognition

ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones

no code implementations24 Aug 2021 Shan An, Guangfu Che, Jinghao Guo, Haogang Zhu, Junjie Ye, Fangru Zhou, Zhaoqi Zhu, Dong Wei, Aishan Liu, Wei zhang

To this concern, this work proposes a real-time augmented reality virtual shoe try-on system for smartphones, namely ARShoe.

Pose Estimation Virtual Try-on

G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation

no code implementations ICCV 2021 Lewei Yao, Renjie Pi, Hang Xu, Wei zhang, Zhenguo Li, Tong Zhang

In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous student-teacher pairs.

Knowledge Distillation Object Detection

Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds

1 code implementation ICCV 2021 Chaoda Zheng, Xu Yan, Jiantao Gao, Weibing Zhao, Wei zhang, Zhen Li, Shuguang Cui

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.

Object Tracking

Binary Complex Neural Network Acceleration on FPGA

no code implementations10 Aug 2021 Hongwu Peng, Shanglin Zhou, Scott Weitze, Jiaxin Li, Sahidul Islam, Tong Geng, Ang Li, Wei zhang, Minghu Song, Mimi Xie, Hang Liu, Caiwen Ding

Deep complex networks (DCN), in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision-making requirements of many deployable systems dealing with short observations or short signal bursts.

Decision Making

Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video

no code implementations9 Aug 2021 Jie Wu, Wei zhang, Guanbin Li, Wenhao Wu, Xiao Tan, YingYing Li, Errui Ding, Liang Lin

In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.

Anomaly Detection

On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation

no code implementations ACL 2021 Wei zhang, Ziming Huang, Yada Zhu, Guangnan Ye, Xiaodong Cui, Fan Zhang

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.

Performance assessment and tuning of PID control using TLBO: the single-loop case and PI/P cascade case

no code implementations31 Jul 2021 Wei zhang, He Dong, Yunlang Xu, Xiaoping Li

Minimum output variance (MOV) is used as a benchmark for CPA of PID, but it is difficult to be found due to the associated non-convex optimization problem.

Stochastic Optimization

Greedy Network Enlarging

no code implementations31 Jul 2021 Chuanjian Liu, Kai Han, An Xiao, Yiping Deng, Wei zhang, Chunjing Xu, Yunhe Wang

Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i. e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet.

Augmentation Pathways Network for Visual Recognition

1 code implementation26 Jul 2021 Yalong Bai, Mohan Zhou, Yuxiang Chen, Wei zhang, BoWen Zhou, Tao Mei

Experimental results on ImageNet benchmarks demonstrate the compatibility and effectiveness on a much wider range of augmentations (e. g., Crop, Gray, Grid Shuffle, RandAugment), while consuming fewer parameters and lower computational costs at inference time.

Data Augmentation

Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data

no code implementations16 Jul 2021 Jiandong Mu, Mengdi Wang, Feiwen Zhu, Jun Yang, Wei Lin, Wei zhang

Reinforcement learning (RL)-based auto-pruning has been further proposed to automate the DNN pruning process to avoid expensive hand-crafted work.

Neural Network Compression Transfer Learning

Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition

no code implementations8 Jul 2021 Wei zhang, Zunhu Guo, Keyu Chen, Lincheng Li, Zhimeng Zhang, Yu Ding

Automatic affective recognition has been an important research topic in human computer interaction (HCI) area.

Emotion Recognition

One Million Scenes for Autonomous Driving: ONCE Dataset

1 code implementation21 Jun 2021 Jiageng Mao, Minzhe Niu, Chenhan Jiang, Hanxue Liang, Jingheng Chen, Xiaodan Liang, Yamin Li, Chaoqiang Ye, Wei zhang, Zhenguo Li, Jie Yu, Hang Xu, Chunjing Xu

To facilitate future research on exploiting unlabeled data for 3D detection, we additionally provide a benchmark in which we reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.

3D Object Detection Autonomous Driving

SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving

no code implementations21 Jun 2021 Jianhua Han, Xiwen Liang, Hang Xu, Kai Chen, Lanqing Hong, Jiageng Mao, Chaoqiang Ye, Wei zhang, Zhenguo Li, Xiaodan Liang, Chunjing Xu

Experiments show that SODA10M can serve as a promising pre-training dataset for different self-supervised learning methods, which gives superior performance when fine-tuning with different downstream tasks (i. e., detection, semantic/instance segmentation) in autonomous driving domain.

Autonomous Driving Instance Segmentation +4

Mesh Saliency: An Independent Perceptual Measure or a Derivative of Image Saliency?

1 code implementation CVPR 2021 Ran Song, Wei zhang, Yitian Zhao, Yonghuai Liu, Paul L. Rosin

While mesh saliency aims to predict regional importance of 3D surfaces in agreement with human visual perception and is well researched in computer vision and graphics, latest work with eye-tracking experiments shows that state-of-the-art mesh saliency methods remain poor at predicting human fixations.

Discrimination-Aware Mechanism for Fine-Grained Representation Learning

no code implementations CVPR 2021 Furong Xu, Meng Wang, Wei zhang, Yuan Cheng, Wei Chu

Therefore, there is a need for a training mechanism that enforces the discriminativeness of all the elements in the feature to capture more the subtle visual cues.

Representation Learning

LPSNet: A Lightweight Solution for Fast Panoptic Segmentation

no code implementations CVPR 2021 Weixiang Hong, Qingpei Guo, Wei zhang, Jingdong Chen, Wei Chu

Panoptic segmentation is a challenging task aiming to simultaneously segment objects (things) at instance level and background contents (stuff) at semantic level.

Instance Segmentation Panoptic Segmentation

Tensor-Based Multi-View Block-Diagonal Structure Diffusion for Clustering Incomplete Multi-View Data

1 code implementation IEEE International Conference on Multimedia and Expo 2021 Zhenglai Li, Chang Tang, Xinwang Liu, Xiao Zheng, Wei zhang, En Zhu

In this paper, we propose a novel incomplete multi-view clustering method, in which a tensor nuclear norm regularizer elegantly diffuses the information of multi-view block-diagonal structure across different views.

Incomplete multi-view clustering

On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation

no code implementations9 Jun 2021 Wei zhang, Ziming Huang, Yada Zhu, Guangnan Ye, Xiaodong Cui, Fan Zhang

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.

Joint Channel Estimation and Mixed-ADCs Allocation for Massive MIMO via Deep Learning

no code implementations8 Jun 2021 Liangyuan Xu, Feifei Gao, Ting Zhou, Shaodan Ma, Wei zhang

Instead of randomly assigning the mixed-ADCs, we then design a novel antenna selection network for mixed-ADCs allocation to further improve the channel estimation accuracy.

Model Aided Deep Learning Based MIMO OFDM Receiver With Nonlinear Power Amplifiers

no code implementations30 May 2021 Liangyuan Xu, Feifei Gao, Wei zhang, Shaodan Ma

Multi-input multi-output orthogonal frequency division multiplexing (MIMO OFDM) is a key technology for mobile communication systems.

Focus on Local: Detecting Lane Marker from Bottom Up via Key Point

no code implementations CVPR 2021 Zhan Qu, Huan Jin, Yang Zhou, Zhen Yang, Wei zhang

Mainstream lane marker detection methods are implemented by predicting the overall structure and deriving parametric curves through post-processing.

Lane Detection

Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation

no code implementations CVPR 2021 Lewei Yao, Renjie Pi, Hang Xu, Wei zhang, Zhenguo Li, Tong Zhang

For student morphism, weight inheritance strategy is adopted, allowing the student to flexibly update its architecture while fully utilize the predecessor's weights, which considerably accelerates the search; To facilitate dynamic distillation, an elastic teacher pool is trained via integrated progressive shrinking strategy, from which teacher detectors can be sampled without additional cost in subsequent searches.

Knowledge Distillation Neural Architecture Search +1

CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks

1 code implementation25 May 2021 Ruchir Puri, David S. Kung, Geert Janssen, Wei zhang, Giacomo Domeniconi, Vladimir Zolotov, Julian Dolby, Jie Chen, Mihir Choudhury, Lindsey Decker, Veronika Thost, Luca Buratti, Saurabh Pujar, Shyam Ramji, Ulrich Finkler, Susan Malaika, Frederick Reiss

In addition to its large scale, CodeNet has a rich set of high-quality annotations to benchmark and help accelerate research in AI techniques for a variety of critical coding tasks, including code similarity and classification, code translation between a large variety of programming languages, and code performance (runtime and memory) improvement techniques.

Code Classification Code Translation

Consensus Graph Learning for Multi-view Clustering

no code implementations IEEE Transactions on Multimedia 2021 Zhenglai Li, Chang Tang, Xinwang Liu, Xiao Zheng, Guanghui Yue, Wei zhang

Furthermore, we unify the spectral embedding and low rank tensor learning into a unified optimization framework to determine the spectral embedding matrices and tensor representation jointly.

Graph Learning

Normalization of Language Embeddings for Cross-Lingual Alignment

1 code implementation NeurIPS 2021 Prince Osei Aboagye, Jeff Phillips, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei zhang, Liang Wang, Hao Yang

Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP.


TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning

no code implementations17 May 2021 Lu Wang, xiaofu Chang, Shuang Li, Yunfei Chu, Hui Li, Wei zhang, Xiaofeng He, Le Song, Jingren Zhou, Hongxia Yang

Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level.

Contrastive Learning Graph Learning +2

Billion-scale Pre-trained E-commerce Product Knowledge Graph Model

no code implementations2 May 2021 Wen Zhang, Chi-Man Wong, Ganqiang Ye, Bo Wen, Wei zhang, Huajun Chen

As a backbone for online shopping platforms, we built a billion-scale e-commerce product knowledge graph for various item knowledge services such as item recommendation.

Knowledge Graphs

Points as Queries: Weakly Semi-supervised Object Detection by Points

no code implementations CVPR 2021 Liangyu Chen, Tong Yang, Xiangyu Zhang, Wei zhang, Jian Sun

We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points.

Object Detection Semi-Supervised Object Detection

Jittering Effects Analysis and Beam Training Design for UAV Millimeter Wave Communications

no code implementations13 Apr 2021 Wei Wang, Wei zhang

In beam training design, with the relationship between attitude angles and AoA/AoD, we propose to generate a rough estimate of AoA and AoD from UAV navigation information.

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

1 code implementation6 Apr 2021 Archit Rathore, Sunipa Dev, Jeff M. Phillips, Vivek Srikumar, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei zhang, Bei Wang

To aid this, we present Visualization of Embedding Representations for deBiasing system ("VERB"), an open-source web-based visualization tool that helps the users gain a technical understanding and visual intuition of the inner workings of debiasing techniques, with a focus on their geometric properties.

Decision Making Dimensionality Reduction +2

UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

1 code implementation CVPR 2021 Tianjiao Li, Jun Liu, Wei zhang, Yun Ni, Wenqian Wang, Zhiheng Li

Human behavior understanding with unmanned aerial vehicles (UAVs) is of great significance for a wide range of applications, which simultaneously brings an urgent demand of large, challenging, and comprehensive benchmarks for the development and evaluation of UAV-based models.

Action Recognition Pedestrian Attribute Recognition +2

Exploiting Relationship for Complex-scene Image Generation

no code implementations1 Apr 2021 Tianyu Hua, Hongdong Zheng, Yalong Bai, Wei zhang, Xiao-Ping Zhang, Tao Mei

Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image.

Image Generation Scene Generation

Source-Free Domain Adaptation for Semantic Segmentation

no code implementations CVPR 2021 Yuang Liu, Wei zhang, Jun Wang

To cope with this issue, we propose a source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation.

Self-Supervised Learning Semantic Segmentation +2

Zero-shot Adversarial Quantization

no code implementations CVPR 2021 Yuang Liu, Wei zhang, Jun Wang

To address the above issues, we propose a zero-shot adversarial quantization (ZAQ) framework, facilitating effective discrepancy estimation and knowledge transfer from a full-precision model to its quantized model.

Quantization Transfer Learning

IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning

no code implementations22 Mar 2021 Wei zhang, Yunfeng Zhang, Ning Liu, Kai Ren, Pengfei Wang

This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL).

Social Link Inference via Multi-View Matching Network from Spatio-Temporal Trajectories

no code implementations20 Mar 2021 Wei zhang, Xin Lai, Jianyong Wang

In this paper, we investigate the problem of social link inference in a target Location-aware Social Network (LSN), which aims at predicting the unobserved links between users within the network.

Link Prediction Time Series

Fast Beam Training and Alignment for IRS-Assisted Millimeter Wave/Terahertz Systems

no code implementations10 Mar 2021 Peilan Wang, Jun Fang, Wei zhang, Hongbin Li

Intelligent reflecting surface (IRS) has emerged as a competitive solution to address blockage issues in millimeter wave (mmWave) and Terahertz (THz) communications due to its capability of reshaping wireless transmission environments.

Adaptive Multi-Teacher Multi-level Knowledge Distillation

1 code implementation6 Mar 2021 Yuang Liu, Wei zhang, Jun Wang

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks.

Knowledge Distillation

Graph-Based Tri-Attention Network for Answer Ranking in CQA

no code implementations5 Mar 2021 Wei zhang, Zeyuan Chen, Chao Dong, Wen Wang, Hongyuan Zha, Jianyong Wang

However, they encounter two main limitations: (1) Correlations between answers in the same question are often overlooked.

Question Answering

Hybrid Interference Mitigation Using Analog Prewhitening

no code implementations4 Mar 2021 Wei zhang, Yi Jiang, Bin Zhou, Die Hu

This paper proposes a novel scheme for mitigating strong interferences, which is applicable to various wireless scenarios, including full-duplex wireless communications and uncoordinated heterogenous networks.

Optically synchronized fiber links with spectrally pure integrated lasers

no code implementations11 Feb 2021 Grant M. Brodnik, Mark W. Harrington, John H. Dallyn, Debapam Bose, Wei zhang, Liron Stern, Paul A. Morton, Ryan O. Behunin, Scott B. Papp, Daniel J. Blumenthal

In this paper we report a record low 3x10^-4 rad^2 residual phase error variance for synchronization based on independent, spectrally pure, ultra-high mutual coherence, photonic integrated lasers.

Optics Applied Physics

Massive Self-Assembly in Grid Environments

no code implementations5 Feb 2021 Wenjie Chu, Wei zhang, Haiyan Zhao, Zhi Jin, Hong Mei

Self-assembly plays an essential role in many natural processes, involving the formation and evolution of living or non-living structures, and shows potential applications in many emerging domains.

Multiagent Systems Distributed, Parallel, and Cluster Computing Robotics

Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation

no code implementations3 Feb 2021 Mingke Xu, Fan Zhang, Xiaodong Cui, Wei zhang

In this paper, we apply multiscale area attention in a deep convolutional neural network to attend emotional characteristics with varied granularities and therefore the classifier can benefit from an ensemble of attentions with different scales.

Data Augmentation Speech Emotion Recognition

MUSE: Multi-Scale Temporal Features Evolution for Knowledge Tracing

no code implementations30 Jan 2021 Chengwei Zhang, Yangzhou Jiang, Wei zhang, Chengyu Gu

The proposed model is capable to capture the dynamic changes in users knowledge states at different temporal-ranges, and provides an efficient and powerful way to combine local and global features to make predictions.

Knowledge Tracing

AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence

no code implementations25 Jan 2021 Yunhe Wang, Mingqiang Huang, Kai Han, Hanting Chen, Wei zhang, Chunjing Xu, DaCheng Tao

With a comprehensive comparison on the performance, power consumption, hardware resource consumption and network generalization capability, we conclude the AdderNet is able to surpass all the other competitors including the classical CNN, novel memristor-network, XNOR-Net and the shift-kernel based network, indicating its great potential in future high performance and energy-efficient artificial intelligence applications.


Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification

no code implementations12 Jan 2021 Xuanyu He, Wei zhang, Ran Song, Qian Zhang, Xiangyuan Lan, Lin Ma

By studying two unsupervised person re-ID methods in a cross-method way, we point out a hard negative problem is handled implicitly by their designs of data augmentations and PK sampler respectively.

Contrastive Learning Unsupervised Person Re-Identification

RRL: A Scalable Classifier for Interpretable Rule-Based Representation Learning

no code implementations1 Jan 2021 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

Rule-based models, e. g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity.

Representation Learning

Double Q-learning: New Analysis and Sharper Finite-time Bound

no code implementations1 Jan 2021 Lin Zhao, Huaqing Xiong, Yingbin Liang, Wei zhang

Double Q-learning (Hasselt 2010) has gained significant success in practice due to its effectiveness in overcoming the overestimation issue of Q-learning.


Why Does Decentralized Training Outperform Synchronous Training In The Large Batch Setting?

no code implementations1 Jan 2021 Wei zhang, Mingrui Liu, Yu Feng, Brian Kingsbury, Yuhai Tu

We conduct extensive studies over 12 state-of-the-art DL models/tasks and demonstrate that DPSGD consistently outperforms SSGD in the large batch setting; and DPSGD converges in cases where SSGD diverges for large learning rates.

Speech Recognition

Exploring Geometry-Aware Contrast and Clustering Harmonization for Self-Supervised 3D Object Detection

no code implementations ICCV 2021 Hanxue Liang, Chenhan Jiang, Dapeng Feng, Xin Chen, Hang Xu, Xiaodan Liang, Wei zhang, Zhenguo Li, Luc van Gool

Here we present a novel self-supervised 3D Object detection framework that seamlessly integrates the geometry-aware contrast and clustering harmonization to lift the unsupervised 3D representation learning, named GCC-3D.

3D Object Detection Representation Learning +1

C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing

no code implementations ICCV 2021 Yanning Zhou, Hang Xu, Wei zhang, Bin Gao, Pheng-Ann Heng

The semi-supervised semantic segmentation methods utilize the unlabeled data to increase the feature discriminative ability to alleviate the burden of the annotated data.

Contrastive Learning Data Augmentation +1

Anomalous Hall and Nernst Effects in FeRh

no code implementations28 Dec 2020 Hilal Saglam, Changjiang Liu, Yi Li, Joseph Sklenar, Jonathan Gibbons, Deshun Hong, Vedat Karakas, John E. Pearson, Ozhan Ozatay, Wei zhang, Anand Bhattacharya, Axel Hoffmann

Antiferromagnets with tunable phase transitions are promising for future spintronics applications.

Materials Science

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

no code implementations24 Dec 2020 Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao GAO, Haitao Long, Quan Yuan

In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.

Imitation Learning Starcraft +1

Hard-ODT: Hardware-Friendly Online Decision Tree Learning Algorithm and System

no code implementations11 Dec 2020 Zhe Lin, Sharad Sinha, Wei zhang

Following this, we present Hard-ODT, a high-performance, hardware-efficient and scalable online decision tree learning system on a field-programmable gate array (FPGA) with system-level optimization techniques.

Improving Relation Extraction with Relational Paraphrase Sentences

1 code implementation COLING 2020 Junjie Yu, Tong Zhu, Wenliang Chen, Wei zhang, Min Zhang

In this paper, we propose an alternative approach to improve RE systems via enriching diverse expressions by relational paraphrase sentences.

Relation Extraction

NUT-RC: Noisy User-generated Text-oriented Reading Comprehension

1 code implementation COLING 2020 Rongtao Huang, Bowei Zou, Yu Hong, Wei zhang, AiTi Aw, Guodong Zhou

Most existing RC models are developed on formal datasets such as news articles and Wikipedia documents, which severely limit their performances when directly applied to the noisy and informal texts in social media.

Answer Selection Multi-Task Learning +1

Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets

2 code implementations NeurIPS 2020 Kai Han, Yunhe Wang, Qiulin Zhang, Wei zhang, Chunjing Xu, Tong Zhang

To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint.

Image Classification

Online Decision Based Visual Tracking via Reinforcement Learning

no code implementations NeurIPS 2020 Ke Song, Wei zhang, Ran Song, Yibin Li

A deep visual tracker is typically based on either object detection or template matching while each of them is only suitable for a particular group of scenes.

Hierarchical Reinforcement Learning Object Detection +2

Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts

no code implementations NeurIPS 2020 Guilin Li, Junlei Zhang, Yunhe Wang, Chuanjian Liu, Matthias Tan, Yunfeng Lin, Wei zhang, Jiashi Feng, Tong Zhang

In particular, we propose a novel joint-training framework to train plain CNN by leveraging the gradients of the ResNet counterpart.

Adam$^+$: A Stochastic Method with Adaptive Variance Reduction

no code implementations24 Nov 2020 Mingrui Liu, Wei zhang, Francesco Orabona, Tianbao Yang

As a result, Adam$^+$ requires few parameter tuning, as Adam, but it enjoys a provable convergence guarantee.

Image Classification Speech Recognition +1

Merchant Category Identification Using Credit Card Transactions

no code implementations5 Nov 2020 Chin-Chia Michael Yeh, Zhongfang Zhuang, Yan Zheng, Liang Wang, Junpeng Wang, Wei zhang

In this work, we approach this problem from a multi-modal learning perspective, where we use not only the merchant time series data but also the information of merchant-merchant relationship (i. e., affinity) to verify the self-reported business type (i. e., merchant category) of a given merchant.

Time Series Time Series Classification

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction

1 code implementation COLING 2020 Tong Zhu, Haitao Wang, Junjie Yu, Xiabing Zhou, Wenliang Chen, Wei zhang, Min Zhang

The experimental results show that the ranking lists of the comparison systems on the DS-labelled test data and human-annotated test data are different.

Relation Extraction

Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction

no code implementations COLING 2020 Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei zhang, Huajun Chen

Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings.

Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets

4 code implementations28 Oct 2020 Kai Han, Yunhe Wang, Qiulin Zhang, Wei zhang, Chunjing Xu, Tong Zhang

To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint.

Image Classification

G-DARTS-A: Groups of Channel Parallel Sampling with Attention

no code implementations16 Oct 2020 Zhaowen Wang, Wei zhang, Zhiming Wang

Differentiable Architecture Search (DARTS) provides a baseline for searching effective network architectures based gradient, but it is accompanied by huge computational overhead in searching and training network architecture.

How Can Self-Attention Networks Recognize Dyck-n Languages?

no code implementations Findings of the Association for Computational Linguistics 2020 Javid Ebrahimi, Dhruv Gelda, Wei zhang

For $\mathcal{D}_2$, we find that SA$^-$ completely breaks down on long sequences whereas the accuracy of SA$^+$ is 58. 82$\%$.

Knowledge Association with Hyperbolic Knowledge Graph Embeddings

1 code implementation EMNLP 2020 Zequn Sun, Muhao Chen, Wei Hu, Chengming Wang, Jian Dai, Wei zhang

Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge representations.

Entity Alignment Knowledge Graph Embeddings +1

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

1 code implementation EMNLP 2020 Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei zhang, Yichi Zhang, Hao Kong, Suhui Wu

On the one hand, sparse KGs contain less information, which makes it difficult for the model to choose correct paths.

Finite-Time Analysis for Double Q-learning

no code implementations NeurIPS 2020 Huaqing Xiong, Lin Zhao, Yingbin Liang, Wei zhang

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values incurred by random sampling.


Kernel Based Progressive Distillation for Adder Neural Networks

no code implementations NeurIPS 2020 Yixing Xu, Chang Xu, Xinghao Chen, Wei zhang, Chunjing Xu, Yunhe Wang

A convolutional neural network (CNN) with the same architecture is simultaneously initialized and trained as a teacher network, features and weights of ANN and CNN will be transformed to a new space to eliminate the accuracy drop.

Knowledge Distillation

TernaryBERT: Distillation-aware Ultra-low Bit BERT

2 code implementations EMNLP 2020 Wei Zhang, Lu Hou, Yichun Yin, Lifeng Shang, Xiao Chen, Xin Jiang, Qun Liu

Transformer-based pre-training models like BERT have achieved remarkable performance in many natural language processing tasks. However, these models are both computation and memory expensive, hindering their deployment to resource-constrained devices.

Knowledge Distillation Quantization

Towards a Flexible Embedding Learning Framework

no code implementations23 Sep 2020 Chin-Chia Michael Yeh, Dhruv Gelda, Zhongfang Zhuang, Yan Zheng, Liang Gou, Wei zhang

Our proposed framework utilizes a set of entity-relation-matrices as the input, which quantifies the affinities among different entities in the database.

Representation Learning

DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning

no code implementations13 Sep 2020 Yushan Zhu, Wen Zhang, Mingyang Chen, Hui Chen, Xu Cheng, Wei zhang, Huajun Chen

In DualDE, we propose a soft label evaluation mechanism to adaptively assign different soft label and hard label weights to different triples, and a two-stage distillation approach to improve the student's acceptance of the teacher.

Knowledge Distillation Knowledge Graph Embedding +2

Decision Tree Based Hardware Power Monitoring for Run Time Dynamic Power Management in FPGA

no code implementations3 Sep 2020 Zhe Lin, Wei zhang, Sharad Sinha

A flexible architecture of the hardware power monitoring is proposed, which can be instrumented in any RTL design for runtime power estimation, dispensing with the need for extra power measurement devices.

An Ensemble Learning Approach for In-situ Monitoring of FPGA Dynamic Power

no code implementations3 Sep 2020 Zhe Lin, Sharad Sinha, Wei zhang

As field-programmable gate arrays become prevalent in critical application domains, their power consumption is of high concern.

Ensemble Learning

Towards Efficient and Scalable Acceleration of Online Decision Tree Learning on FPGA

no code implementations3 Sep 2020 Zhe Lin, Sharad Sinha, Wei zhang

We further present a high-performance, hardware-efficient and scalable online decision tree learning system on a field-programmable gate array (FPGA) with system-level optimization techniques.

Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator

no code implementations30 Aug 2020 Yue Fan, Shilei Chu, Wei zhang, Ran Song, Yibin Li

Extensive experiments are conducted to demonstrate the accuracy of the proposed imitating learning process as well as the reliability of the holistic system for autonomous drone navigation.

Drone navigation Imitation Learning

Products-10K: A Large-scale Product Recognition Dataset

no code implementations24 Aug 2020 Yalong Bai, Yuxiang Chen, Wei Yu, Linfang Wang, Wei zhang

With the rapid development of electronic commerce, the way of shopping has experienced a revolutionary evolution.

A(DP)$^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy

no code implementations21 Aug 2020 Jie Xu, Wei zhang, Fei Wang

A popular distributed learning strategy is federated learning, where there is a central server storing the global model and a set of local computing nodes updating the model parameters with their corresponding data.

Federated Learning

Cluster-level Feature Alignment for Person Re-identification

1 code implementation15 Aug 2020 Qiuyu Chen, Wei zhang, Jianping Fan

Instance-level alignment is widely exploited for person re-identification, e. g. spatial alignment, latent semantic alignment and triplet alignment.

Person Re-Identification

Pneumonia after bacterial or viral infection preceded or followed by radiation exposure -- a reanalysis of older radiobiological data and implications for low dose radiotherapy for COVID-19 pneumonia

no code implementations6 Aug 2020 Mark P Little, Wei zhang, Roy van Dusen, Nobuyuki Hamada

For 7 studies that evaluated post-inoculation radiation exposure (more relevant to LDRT for COVID-19 pneumonia) the results are heterogeneous, with 2 studies showing a significant increase (p<0. 001) and another showing a significant decrease (p<0. 001) in mortality associated with radiation exposure.

Momentum Q-learning with Finite-Sample Convergence Guarantee

no code implementations30 Jul 2020 Bowen Weng, Huaqing Xiong, Lin Zhao, Yingbin Liang, Wei zhang

For the infinite state-action space case, we establish the convergence guarantee for MomentumQ with linear function approximations and Markovian sampling.


Research Progress of Convolutional Neural Network and its Application in Object Detection

no code implementations27 Jul 2020 Wei Zhang, Zuoxiang Zeng

With the improvement of computer performance and the increase of data volume, the object detection based on convolutional neural network (CNN) has become the main algorithm for object detection.

Object Detection

Multi-stream RNN for Merchant Transaction Prediction

no code implementations25 Jul 2020 Zhongfang Zhuang, Chin-Chia Michael Yeh, Liang Wang, Wei zhang, Junpeng Wang

New challenges have surfaced in monitoring and guaranteeing the integrity of payment processing systems.

Fraud Detection Time Series

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

1 code implementation ECCV 2020 Hang Xu, Shaoju Wang, Xinyue Cai, Wei zhang, Xiaodan Liang, Zhenguo Li

In this paper, we propose a novel lane-sensitive architecture search framework named CurveLane-NAS to automatically capture both long-ranged coherent and accurate short-range curve information while unifying both architecture search and post-processing on curve lane predictions via point blending.

Autonomous Driving Lane Detection

Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

1 code implementation ECCV 2020 Haoran Wang, Tong Shen, Wei zhang, Ling-Yu Duan, Tao Mei

To fully exploit the supervision in the source domain, we propose a fine-grained adversarial learning strategy for class-level feature alignment while preserving the internal structure of semantics across domains.

Domain Adaptation Semantic Segmentation +1

Automatic Image Labelling at Pixel Level

no code implementations15 Jul 2020 Xiang Zhang, Wei zhang, Jinye Peng, Jianping Fan

A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from a source domain, and such GFN then transfers such segmentation knowledge to generate coarse object masks in the target domain.

Semantic Segmentation

Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent

no code implementations15 Jul 2020 Bowen Weng, Huaqing Xiong, Yingbin Liang, Wei zhang

In this paper, we first characterize the convergence rate for Q-AMSGrad, which is the Q-learning algorithm with AMSGrad update (a commonly adopted alternative of Adam for theoretical analysis).

Atari Games Q-Learning

Multi-future Merchant Transaction Prediction

no code implementations10 Jul 2020 Chin-Chia Michael Yeh, Zhongfang Zhuang, Wei zhang, Liang Wang

We use experiments on real-world merchant transaction data to demonstrate the effectiveness of our proposed model.

Fraud Detection Future prediction +3

PointTrack++ for Effective Online Multi-Object Tracking and Segmentation

1 code implementation3 Jul 2020 Zhenbo Xu, Wei zhang, Xiao Tan, Wei Yang, Xiangbo Su, Yuchen Yuan, Hongwu Zhang, Shilei Wen, Errui Ding, Liusheng Huang

In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.

Data Augmentation Instance Segmentation +5

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

1 code implementation ECCV 2020 Zhenbo Xu, Wei zhang, Xiao Tan, Wei Yang, Huan Huang, Shilei Wen, Errui Ding, Liusheng Huang

The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5. 4% higher MOTSA and 18 times faster over MOTSFusion) with the near real-time speed (22 FPS).

Multi-Object Tracking Multi-Object Tracking and Segmentation +1

GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation

1 code implementation5 Jun 2020 Aravind Sankar, Yanhong Wu, Yuhang Wu, Wei zhang, Hao Yang, Hari Sundaram

We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together.

FP-Stereo: Hardware-Efficient Stereo Vision for Embedded Applications

no code implementations5 Jun 2020 Jieru Zhao, Tingyuan Liang, Liang Feng, Wenchao Ding, Sharad Sinha, Wei zhang, Shaojie Shen

To reduce the design effort and achieve the right balance, we propose FP-Stereo for building high-performance stereo matching pipelines on FPGAs automatically.

Depth Estimation Stereo Matching

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

1 code implementation CVPR 2021 Zhaohui Yang, Yunhe Wang, Xinghao Chen, Jianyuan Guo, Wei zhang, Chao Xu, Chunjing Xu, DaCheng Tao, Chang Xu

To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search.

Neural Architecture Search

Map Generation from Large Scale Incomplete and Inaccurate Data Labels

no code implementations20 May 2020 Rui Zhang, Conrad Albrecht, Wei zhang, Xiaodong Cui, Ulrich Finkler, David Kung, Siyuan Lu

Accurately and globally mapping human infrastructure is an important and challenging task with applications in routing, regulation compliance monitoring, and natural disaster response management etc..

Disaster Response

Learning from a Lightweight Teacher for Efficient Knowledge Distillation

no code implementations19 May 2020 Yuang Liu, Wei zhang, Jun Wang

Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers.

Knowledge Distillation

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

no code implementations CVPR 2020 Qiuyu Chen, Wei zhang, Ning Zhou, Peng Lei, Yi Xu, Yu Zheng, Jianping Fan

Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling.

Look-into-Object: Self-supervised Structure Modeling for Object Recognition

2 code implementations CVPR 2020 Mohan Zhou, Yalong Bai, Wei zhang, Tiejun Zhao, Tao Mei

Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category.

Fine-Grained Image Classification Image Recognition +5

Sex Differences in Severity and Mortality Among Patients With COVID-19: Evidence from Pooled Literature Analysis and Insights from Integrated Bioinformatic Analysis

no code implementations30 Mar 2020 Xiyi Wei, Yu-Tian Xiao, Jian Wang, Rui Chen, Wei zhang, Yue Yang, Daojun Lv, Chao Qin, Di Gu, Bo Zhang, Weidong Chen, Jianquan Hou, Ninghong Song, Guohua Zeng, Shancheng Ren

Objective: To conduct a meta-analysis of current studies that examined sex differences in severity and mortality in patients with COVID-19, and identify potential mechanisms underpinning these differences.

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

1 code implementation1 Mar 2020 Zhenbo Xu, Wei zhang, Xiaoqing Ye, Xiao Tan, Wei Yang, Shilei Wen, Errui Ding, Ajin Meng, Liusheng Huang

The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes.

3D Object Detection Autonomous Driving +1

Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition

no code implementations24 Feb 2020 Xiaodong Cui, Wei zhang, Ulrich Finkler, George Saon, Michael Picheny, David Kung

The past decade has witnessed great progress in Automatic Speech Recognition (ASR) due to advances in deep learning.

Speech Recognition

Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network

no code implementations20 Feb 2020 Yuanyuan Jin, Wei zhang, Xiangnan He, Xinyu Wang, Xiaoling Wang

Given a set of symptoms to treat, we aim to generate an overall syndrome representation by effectively fusing the embeddings of all the symptoms in the set, to mimic how a doctor induces the syndromes.

Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction

1 code implementation19 Feb 2020 Wen Wang, Wei zhang, Shukai Liu, Qi Liu, Bo Zhang, Leyu Lin, Hongyuan Zha

Specifically, we build a Multi-Relational Item Graph (MRIG) based on all behavior sequences from all sessions, involving target and auxiliary behavior types.

Representation Learning

CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

1 code implementation ICML 2020 Wei Zhang, Thomas Kobber Panum, Somesh Jha, Prasad Chalasani, David Page

We study the problem of learning Granger causality between event types from asynchronous, interdependent, multi-type event sequences.

Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling

no code implementations15 Feb 2020 Huaqing Xiong, Tengyu Xu, Yingbin Liang, Wei zhang

Despite the wide applications of Adam in reinforcement learning (RL), the theoretical convergence of Adam-type RL algorithms has not been established.

Distributed Bayesian Matrix Decomposition for Big Data Mining and Clustering

2 code implementations10 Feb 2020 Chihao Zhang, Yang Yang, Wei zhang, Shihua Zhang

Such a method should scale up well, model the heterogeneous noise, and address the communication issue in a distributed system.

Distributed Computing

Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption

no code implementations AAAI Conference on Artificial Intelligence (AAAI 2020) 2020 Wei Zhang, Yue Ying, Pan Lu, Hongyuan Zha

Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users’ writing style and traits, and is more practical to meet users’ real demands.

Image Captioning

Improving Efficiency in Large-Scale Decentralized Distributed Training

no code implementations4 Feb 2020 Wei Zhang, Xiaodong Cui, Abdullah Kayi, Mingrui Liu, Ulrich Finkler, Brian Kingsbury, George Saon, Youssef Mroueh, Alper Buyuktosunoglu, Payel Das, David Kung, Michael Picheny

Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchronous Parallel SGD (AD-PSGD) is a family of distributed learning algorithms that have been demonstrated to perform well for large-scale deep learning tasks.

Speech Recognition

Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning

1 code implementation1 Feb 2020 Qianming Xue, Wei zhang, Hongyuan Zha

To improve domain-adapted sentiment classification by learning sentiment from the target domain as well, we devise a novel deep adversarial mutual learning approach involving two groups of feature extractors, domain discriminators, sentiment classifiers, and label probers.

General Classification Sentiment Analysis

How Does BN Increase Collapsed Neural Network Filters?

no code implementations30 Jan 2020 Sheng Zhou, Xinjiang Wang, Ping Luo, Litong Feng, Wenjie Li, Wei zhang

This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.

Object Detection

Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization

1 code implementation ICLR 2020 Junjie Yan, Ruosi Wan, Xiangyu Zhang, Wei zhang, Yichen Wei, Jian Sun

Therefore many modified normalization techniques have been proposed, which either fail to restore the performance of BN completely, or have to introduce additional nonlinear operations in inference procedure and increase huge consumption.

Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets

no code implementations ICLR 2020 Mingrui Liu, Youssef Mroueh, Jerret Ross, Wei zhang, Xiaodong Cui, Payel Das, Tianbao Yang

Then we propose an adaptive variant of OSG named Optimistic Adagrad (OAdagrad) and reveal an \emph{improved} adaptive complexity $O\left(\epsilon^{-\frac{2}{1-\alpha}}\right)$, where $\alpha$ characterizes the growth rate of the cumulative stochastic gradient and $0\leq \alpha\leq 1/2$.

Down to the Last Detail: Virtual Try-on with Detail Carving

2 code implementations13 Dec 2019 Jiahang Wang, Wei zhang, Weizhong Liu, Tao Mei

However, existing methods can hardly preserve the details in clothing texture and facial identity (face, hair) while fitting novel clothes and poses onto a person.

Virtual Try-on

Zooming into Face Forensics: A Pixel-level Analysis

no code implementations12 Dec 2019 Jia Li, Tong Shen, Wei zhang, Hui Ren, Dan Zeng, Tao Mei

The stunning progress in face manipulation methods has made it possible to synthesize realistic fake face images, which poses potential threats to our society.

General Classification

Transparent Classification with Multilayer Logical Perceptrons and Random Binarization

1 code implementation10 Dec 2019 Zhuo Wang, Wei zhang, Ning Liu, Jianyong Wang

In this paper, we propose a new hierarchical rule-based model for classification tasks, named Concept Rule Sets (CRS), which has both a strong expressive ability and a transparent inner structure.

Binarization General Classification

Attentive Representation Learning with Adversarial Training for Short Text Clustering

no code implementations8 Dec 2019 Wei Zhang, Chao Dong, Jianhua Yin, Jianyong Wang

Relying on this, the representation learning and clustering for short texts are seamlessly integrated into a unified model.

Information Retrieval Representation Learning +1

AutoBlock: A Hands-off Blocking Framework for Entity Matching

1 code implementation7 Dec 2019 Wei Zhang, Hao Wei, Bunyamin Sisman, Xin Luna Dong, Christos Faloutsos, David Page

Entity matching seeks to identify data records over one or multiple data sources that refer to the same real-world entity.

Entity Resolution Representation Learning

Improving Neural Relation Extraction with Positive and Unlabeled Learning

no code implementations28 Nov 2019 Zhengqiu He, Wenliang Chen, Yuyi Wang, Wei zhang, Guanchun Wang, Min Zhang

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning.

Relation Extraction

Learning Efficient Video Representation with Video Shuffle Networks

no code implementations26 Nov 2019 Pingchuan Ma, Yao Zhou, Yu Lu, Wei zhang

To this end, we propose the video shuffle, a parameter-free plug-in component that efficiently reallocates the inputs of 2D convolution so that its receptive field can be extended to the temporal dimension.

Video Recognition

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

no code implementations22 Nov 2019 Lewei Yao, Hang Xu, Wei zhang, Xiaodan Liang, Zhenguo Li

In this paper, we present a two-stage coarse-to-fine searching strategy named Structural-to-Modular NAS (SM-NAS) for searching a GPU-friendly design of both an efficient combination of modules and better modular-level architecture for object detection.

Neural Architecture Search Object Detection

Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset

no code implementations21 Nov 2019 Bingyuan Liu, Jiantao Zhang, Xiaoting Zhang, Wei zhang, Chuanhui Yu, Yuan Zhou

However, few works focus on the understanding of furniture within the scenes and a large-scale dataset is also lacked to advance the field.