Search Results for author: Zhe Wang

Found 145 papers, 55 papers with code

SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation

1 code implementation15 Mar 2023 Siqi Fan, Zhe Wang, Yan Wang, Jingjing Liu

For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology, especially in challenging lighting conditions.

Data Augmentation Semi-Supervised Semantic Segmentation +1

Calibration-free BEV Representation for Infrastructure Perception

no code implementations7 Mar 2023 Siqi Fan, Zhe Wang, Xiaoliang Huo, Yan Wang, Jingjing Liu

Effective BEV object detection on infrastructure can greatly improve traffic scenes understanding and vehicle-toinfrastructure (V2I) cooperative perception.

object-detection Object Detection

MetaGrad: Adaptive Gradient Quantization with Hypernetworks

no code implementations4 Mar 2023 Kaixin Xu, Alina Hui Xiu Lee, Ziyuan Zhao, Zhe Wang, Min Wu, Weisi Lin

A popular track of network compression approach is Quantization aware Training (QAT), which accelerates the forward pass during the neural network training and inference.


Key-Exchange Convolutional Auto-Encoder for Data Augmentation in Early Knee OsteoArthritis Classification

no code implementations26 Feb 2023 Zhe Wang, Aladine Chetouani, Rachid Jennane

In this paper, we propose a learning model based on the convolutional Auto-Encoder and a hybrid loss strategy to generate new data for early KOA (KL-0 vs KL-2) diagnosis.

Data Augmentation

Improving Interpretability via Explicit Word Interaction Graph Layer

1 code implementation3 Feb 2023 Arshdeep Sekhon, Hanjie Chen, Aman Shrivastava, Zhe Wang, Yangfeng Ji, Yanjun Qi

Recent NLP literature has seen growing interest in improving model interpretability.

ConQueR: Query Contrast Voxel-DETR for 3D Object Detection

1 code implementation14 Dec 2022 Benjin Zhu, Zhe Wang, Shaoshuai Shi, Hang Xu, Lanqing Hong, Hongsheng Li

We thus propose a Query Contrast mechanism to explicitly enhance queries towards their best-matched GTs over all unmatched query predictions.

3D Object Detection object-detection

STILN: A Novel Spatial-Temporal Information Learning Network for EEG-based Emotion Recognition

no code implementations22 Nov 2022 Yiheng Tang, Yongxiong Wang, Xiaoli Zhang, Zhe Wang

In the temporal contexts learning, we adopt the Bidirectional Long Short-Term Memory Network (Bi-LSTM) network to capture the dependencies among the EEG frames.

EEG Emotion Recognition

Temporal-spatial Representation Learning Transformer for EEG-based Emotion Recognition

no code implementations16 Nov 2022 Zhe Wang, Yongxiong Wang, Chuanfei Hu, Zhong Yin, Yu Song

Both the temporal dynamics and spatial correlations of Electroencephalogram (EEG), which contain discriminative emotion information, are essential for the emotion recognition.

EEG Emotion Recognition +1

Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control

no code implementations4 Nov 2022 Ziyan Yin, Zhe Wang, Jun Li, Ming Ding, Wen Chen, Shi Jin

The explosive growth of dynamic and heterogeneous data traffic brings great challenges for 5G and beyond mobile networks.

Federated Learning reinforcement-learning +1

Fast DistilBERT on CPUs

2 code implementations27 Oct 2022 Haihao Shen, Ofir Zafrir, Bo Dong, Hengyu Meng, Xinyu Ye, Zhe Wang, Yi Ding, Hanwen Chang, Guy Boudoukh, Moshe Wasserblat

In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators.

Knowledge Distillation Model Compression +2

Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function

no code implementations26 Oct 2022 Qing Wang, Hang Chen, Ya Jiang, Zhe Wang, Yuyang Wang, Jun Du, Chin-Hui Lee

In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.

ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition

no code implementations25 Oct 2022 Chuanfei Hu, Hang Shao, Bo Dong, Zhe Wang, Yongxiong Wang

Representing the spatial properties of facial attributes is a vital challenge for facial attribute recognition (FAR).

Towards Trustworthy Multi-label Sewer Defect Classification via Evidential Deep Learning

no code implementations25 Oct 2022 Chenyang Zhao, Chuanfei Hu, Hang Shao, Zhe Wang, Yongxiong Wang

An automatic vision-based sewer inspection plays a key role of sewage system in a modern city.

Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering

1 code implementation19 Oct 2022 Yaming Yang, Ziyu Guan, Zhe Wang, Wei Zhao, Cai Xu, Weigang Lu, Jianbin Huang

The two modules can effectively utilize and enhance each other, promoting the model to learn discriminative embeddings.

FreGAN: Exploiting Frequency Components for Training GANs under Limited Data

1 code implementation11 Oct 2022 Mengping Yang, Zhe Wang, Ziqiu Chi, Yanbing Zhang

Training GANs under limited data often leads to discriminator overfitting and memorization issues, causing divergent training.


Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile

no code implementations26 Sep 2022 Renzo Andri, Beatrice Bussolino, Antonio Cipolletta, Lukas Cavigelli, Zhe Wang

The Winograd-enhanced DSA achieves up to 1. 85x gain in energy efficiency and up to 1. 83x end-to-end speed-up for state-of-the-art segmentation and detection networks.


Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments

no code implementations22 Sep 2022 Ian Gemp, Thomas Anthony, Yoram Bachrach, Avishkar Bhoopchand, Kalesha Bullard, Jerome Connor, Vibhavari Dasagi, Bart De Vylder, Edgar Duenez-Guzman, Romuald Elie, Richard Everett, Daniel Hennes, Edward Hughes, Mina Khan, Marc Lanctot, Kate Larson, Guy Lever, SiQi Liu, Luke Marris, Kevin R. McKee, Paul Muller, Julien Perolat, Florian Strub, Andrea Tacchetti, Eugene Tarassov, Zhe Wang, Karl Tuyls

The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks.

reinforcement-learning reinforcement Learning

Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning

no code implementations19 Sep 2022 Zhe Wang, Hongsheng Li, Qinwei Zhang, Jing Yuan, Xiaogang Wang

Adaptively learning a distance metric from the undersampled training data can significantly improve the matching accuracy of the query fingerprints.

Magnetic Resonance Fingerprinting Metric Learning

PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation

1 code implementation16 Sep 2022 Haoyu Ma, Zhe Wang, Yifei Chen, Deying Kong, Liangjian Chen, Xingwei Liu, Xiangyi Yan, Hao Tang, Xiaohui Xie

In this paper, we propose the token-Pruned Pose Transformer (PPT) for 2D human pose estimation, which can locate a rough human mask and performs self-attention only within selected tokens.

 Ranked #1 on 3D Human Pose Estimation on Human3.6M (Multi-View or Monocular metric, using extra training data)

2D Human Pose Estimation 3D Human Pose Estimation

Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection

1 code implementation7 Sep 2022 Qiang Xu, Shan Jia, Xinghao Jiang, Tanfeng Sun, Zhe Wang, Hong Yan

Based on the finding that multiple different modules in image acquisition will lead to different sensitivity inconsistencies to the convolutional neural network (CNN)-based rendering in images, we propose a deep texture rendering module for texture difference enhancement and discriminative texture representation.

Semantic Segmentation

A Brief History of Recommender Systems

no code implementations5 Sep 2022 Zhenhua Dong, Zhe Wang, Jun Xu, Ruiming Tang, JiRong Wen

Soon after the invention of the Internet, the recommender system emerged and related technologies have been extensively studied and applied by both academia and industry.

Recommendation Systems

AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query

no code implementations15 Aug 2022 Zepeng Huai, Zhe Wang, Yifan Zhu, Peng Zhang

Paper recommendation with user-generated keyword is to suggest papers that simultaneously meet user's interests and are relevant to the input keyword.

Click-Through Rate Prediction Graph Representation Learning +1

Subtype-Former: a deep learning approach for cancer subtype discovery with multi-omics data

no code implementations28 Jul 2022 Hai Yang, Yuhang Sheng, Yi Jiang, Xiaoyang Fang, Dongdong Li, Jing Zhang, Zhe Wang

In addition, Subtype-Former also achieved outstanding results in pan-cancer subtyping, which can help analyze the commonalities and differences across various cancer types at the molecular level.

Survival Analysis

WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation

1 code implementation15 Jul 2022 Mengping Yang, Zhe Wang, Ziqiu Chi, Wenyi Feng

Concretely, we disentangle encoded features into multiple frequency components and perform low-frequency skip connections to preserve outline and structural information.

Image Generation

Towards Efficient 3D Object Detection with Knowledge Distillation

1 code implementation30 May 2022 Jihan Yang, Shaoshuai Shi, Runyu Ding, Zhe Wang, Xiaojuan Qi

Then, we build a benchmark to assess existing KD methods developed in the 2D domain for 3D object detection upon six well-constructed teacher-student pairs.

3D Object Detection Knowledge Distillation +2

Online Adversarial Distillation for Graph Neural Networks

no code implementations28 Dec 2021 Can Wang, Zhe Wang, Defang Chen, Sheng Zhou, Yan Feng, Chun Chen

However, its effect on graph neural networks is less than satisfactory since the graph topology and node attributes are likely to change in a dynamic way and in this case a static teacher model is insufficient in guiding student training.

Knowledge Distillation

Deep self-consistent learning of local volatility

no code implementations9 Dec 2021 Zhe Wang, Nicolas Privault, Claude Guet

We present an algorithm for the calibration of local volatility from market option prices through deep self-consistent learning, by approximating market option prices and local volatility using deep neural networks.

AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach

no code implementations9 Dec 2021 Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Yuexin Ma, Zhe Wang, Jianping Shi

Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.

Domain Adaptation Stereo Matching

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation

1 code implementation18 Oct 2021 Haoyu Ma, Liangjian Chen, Deying Kong, Zhe Wang, Xingwei Liu, Hao Tang, Xiangyi Yan, Yusheng Xie, Shih-Yao Lin, Xiaohui Xie

The 3D position encoding guided by the epipolar field provides an efficient way of encoding correspondences between pixels of different views.

Ranked #14 on 3D Human Pose Estimation on Human3.6M (using extra training data)

3D Human Pose Estimation 3D Pose Estimation

A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization

no code implementations14 Oct 2021 Ziyi Chen, Zhengyang Hu, Qunwei Li, Zhe Wang, Yi Zhou

However, GDA has been proved to converge to stationary points for nonconvex minimax optimization, which are suboptimal compared with local minimax points.

Delving into Channels: Exploring Hyperparameter Space of Channel Bit Widths with Linear Complexity

no code implementations29 Sep 2021 Zhe Wang, Jie Lin, Xue Geng, Mohamed M. Sabry Aly, Vijay Chandrasekhar

We formulate the quantization of deep neural networks as a rate-distortion optimization problem, and present an ultra-fast algorithm to search the bit allocation of channels.


ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning

no code implementations27 Sep 2021 Zhe Wang, Jake Grigsby, Arshdeep Sekhon, Yanjun Qi

This paper proposes a novel method, ST-MAML, that empowers model-agnostic meta-learning (MAML) to learn from multiple task distributions.

Few-Shot Image Classification Meta-Learning

Long-Range Transformers for Dynamic Spatiotemporal Forecasting

1 code implementation24 Sep 2021 Jake Grigsby, Zhe Wang, Yanjun Qi

Multivariate Time Series Forecasting focuses on the prediction of future values based on historical context.

Multivariate Time Series Forecasting

Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization

2 code implementations26 Aug 2021 Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang, Ling Fan, Zhe Wang

In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization.

Abstractive Text Summarization Contrastive Learning +1

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

no code implementations15 Aug 2021 Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

These specific designs enable the detector to be trained on meticulously refined pseudo labeled target data with denoised training signals, and thus effectively facilitate adapting an object detector to a target domain without requiring annotations.

3D Object Detection Data Augmentation +4

POSO: Personalized Cold Start Modules for Large-scale Recommender Systems

no code implementations10 Aug 2021 Shangfeng Dai, Haobin Lin, Zhichen Zhao, Jianying Lin, Honghuan Wu, Zhe Wang, Sen yang, Ji Liu

Moreover, POSO can be further generalized to regular users, inactive users and returning users (+2%-3% on Watch Time), as well as item cold start (+3. 8% on Watch Time).

Recommendation Systems

A Credibility-aware Swarm-Federated Deep Learning Framework in Internet of Vehicles

1 code implementation9 Aug 2021 Zhe Wang, Xinhang Li, Tianhao Wu, Chen Xu, Lin Zhang

This paper proposes a Swarm-Federated Deep Learning framework in the IoV system (IoV-SFDL) that integrates SL into the FDL framework.

BIG-bench Machine Learning Edge-computing

Reconstructing a dynamical system and forecasting time series by self-consistent deep learning

no code implementations4 Aug 2021 Zhe Wang, Claude Guet

We introduce a self-consistent deep-learning framework which, for a noisy deterministic time series, provides unsupervised filtering, state-space reconstruction, identification of the underlying differential equations and forecasting.

Time Series Analysis

SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation

no code implementations29 May 2021 Zhe Wang, Hao Chen, Xinyu Li, Chunhui Liu, Yuanjun Xiong, Joseph Tighe, Charless Fowlkes

However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset.

Action Parsing Action Segmentation +2

From Motor Control to Team Play in Simulated Humanoid Football

1 code implementation25 May 2021 SiQi Liu, Guy Lever, Zhe Wang, Josh Merel, S. M. Ali Eslami, Daniel Hennes, Wojciech M. Czarnecki, Yuval Tassa, Shayegan Omidshafiei, Abbas Abdolmaleki, Noah Y. Siegel, Leonard Hasenclever, Luke Marris, Saran Tunyasuvunakool, H. Francis Song, Markus Wulfmeier, Paul Muller, Tuomas Haarnoja, Brendan D. Tracey, Karl Tuyls, Thore Graepel, Nicolas Heess

In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds.

Imitation Learning Multi-agent Reinforcement Learning +1

Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field

no code implementations11 May 2021 Zhe Wang, Claude Guet

The present work's objective is two-fold, first to show how an a priori knowledge can be incorporated into neural networks to achieve efficient learning and second to apply the method and study how the induced field and polarizability change when a dielectric particle progressively changes its shape from a sphere to a cube.

Learning Versatile Neural Architectures by Propagating Network Codes

1 code implementation ICLR 2022 Mingyu Ding, Yuqi Huo, Haoyu Lu, Linjie Yang, Zhe Wang, Zhiwu Lu, Jingdong Wang, Ping Luo

(4) Thorough studies of NCP on inter-, cross-, and intra-tasks highlight the importance of cross-task neural architecture design, i. e., multitask neural architectures and architecture transferring between different tasks.

Image Segmentation Neural Architecture Search +2

PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos

no code implementations16 Mar 2021 Tianyu Luan, Yali Wang, Junhao Zhang, Zhe Wang, Zhipeng Zhou, Yu Qiao

By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module.

3D Human Pose Estimation Human Mesh Recovery

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

1 code implementation CVPR 2021 Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation.

3D Object Detection Data Augmentation +3

Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG

no code implementations3 Mar 2021 Arshdeep Sekhon, Zhe Wang, Yanjun Qi

Understanding relationships between feature variables is one important way humans use to make decisions.

Network Pruning via Resource Reallocation

1 code implementation2 Mar 2021 Yuenan Hou, Zheng Ma, Chunxiao Liu, Zhe Wang, Chen Change Loy

Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network.

Network Pruning

FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data

no code implementations6 Feb 2021 Yuxiao Lu, Jie Lin, Chao Jin, Zhe Wang, Min Wu, Khin Mi Mi Aung, XiaoLi Li

Despite the faster HECNN inference, the mainstream packing schemes Dense Packing (DensePack) and Convolution Packing (ConvPack) introduce expensive rotation overhead, which prolongs the inference latency of HECNN for deeper and wider CNN architectures.

Privacy Preserving

Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy

1 code implementation29 Dec 2020 Shuang Xu, Lizhen Ji, Zhe Wang, Pengfei Li, Kai Sun, Chunxia Zhang, Jiangshe Zhang

According to the idea that each local region in the fused image should be similar to the sharpest one among source images, this paper presents an optimization-based approach to reduce defocus spread effects.


Exploring Data Augmentation for Multi-Modality 3D Object Detection

6 code implementations23 Dec 2020 Wenwei Zhang, Zhe Wang, Chen Change Loy

Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation.

3D Object Detection Autonomous Driving +2

A Multi-intersection Vehicular Cooperative Control based on End-Edge-Cloud Computing

no code implementations1 Dec 2020 Mingzhi Jiang, Tianhao Wu, Zhe Wang, Yi Gong, Lin Zhang, Ren Ping Liu

In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections.


Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving

no code implementations27 Nov 2020 Zhenxun Yuan, Xiao Song, Lei Bai, Wengang Zhou, Zhe Wang, Wanli Ouyang

As a special design of this transformer, the information encoded in the encoder is different from that in the decoder, i. e. the encoder encodes temporal-channel information of multiple frames while the decoder decodes the spatial-channel information for the current frame in a voxel-wise manner.

3D Object Detection Autonomous Driving +2

The ANTARES Astronomical Time-Domain Event Broker

no code implementations24 Nov 2020 Thomas Matheson, Carl Stubens, Nicholas Wolf, Chien-Hsiu Lee, Gautham Narayan, Abhijit Saha, Adam Scott, Monika Soraisam, Adam S. Bolton, Benjamin Hauger, David R. Silva, John Kececioglu, Carlos Scheidegger, Richard Snodgrass, Patrick D. Aleo, Eric Evans-Jacquez, Navdeep Singh, Zhe Wang, Shuo Yang, Zhenge Zhao

We describe the Arizona-NOIRLab Temporal Analysis and Response to Events System (ANTARES), a software instrument designed to process large-scale streams of astronomical time-domain alerts.

Instrumentation and Methods for Astrophysics

FLAVA: Find, Localize, Adjust and Verify to Annotate LiDAR-Based Point Clouds

no code implementations20 Nov 2020 Tai Wang, Conghui He, Zhe Wang, Jianping Shi, Dahua Lin

Recent years have witnessed the rapid progress of perception algorithms on top of LiDAR, a widely adopted sensor for autonomous driving systems.

Autonomous Driving

Energy Consumption and Battery Aging Minimization Using a Q-learning Strategy for a Battery/Ultracapacitor Electric Vehicle

no code implementations27 Oct 2020 Bin Xu, Junzhe Shi, Sixu Li, Huayi Li, Zhe Wang

Then, the result from a vehicle without ultracapacitor is used as the baseline, which is compared with the results from the vehicle with ultracapacitor using Q-learning, and two heuristic methods as the energy management strategies.

energy management Management +1

Learning Time Reduction Using Warm Start Methods for a Reinforcement Learning Based Supervisory Control in Hybrid Electric Vehicle Applications

no code implementations27 Oct 2020 Bin Xu, Jun Hou, Junzhe Shi, Huayi Li, Dhruvang Rathod, Zhe Wang, Zoran Filipi

This study aims to reduce the learning iterations of Q-learning in HEV application and improve fuel consumption in initial learning phases utilizing warm start methods.


Topic-Guided Abstractive Text Summarization: a Joint Learning Approach

1 code implementation20 Oct 2020 Chujie Zheng, Kunpeng Zhang, Harry Jiannan Wang, Ling Fan, Zhe Wang

We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content.

Abstractive Text Summarization Extractive Summarization

Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization

no code implementations28 Sep 2020 Tengyu Xu, Zhe Wang, Yingbin Liang, H. Vincent Poor

Specifically, a novel variance reduction algorithm SREDA was proposed recently by (Luo et al. 2020) to solve such a problem, and was shown to achieve the optimal complexity dependence on the required accuracy level $\epsilon$.

Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference

1 code implementation24 Aug 2020 Xiaohong Liu, Kangdi Shi, Zhe Wang, Jun Chen

Extensive experiments demonstrate that owing to the informativeness of the camera raw data, the effectiveness of the network architecture, and the separation of super-resolution and color correction processes, the proposed method achieves superior VSR results compared to the state-of-the-art and can be adapted to any specific camera-ISP.

Informativeness Video Super-Resolution

Spectral Algorithms for Community Detection in Directed Networks

no code implementations9 Aug 2020 Zhe Wang, Yingbin Liang, Pengsheng Ji

Community detection in large social networks is affected by degree heterogeneity of nodes.

Community Detection

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

3 code implementations4 Aug 2020 Hui Zhou, Xinge Zhu, Xiao Song, Yuexin Ma, Zhe Wang, Hongsheng Li, Dahua Lin

A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space.

3D Semantic Segmentation LIDAR Semantic Segmentation

COLD: Towards the Next Generation of Pre-Ranking System

2 code implementations31 Jul 2020 Zhe Wang, Liqin Zhao, Biye Jiang, Guorui Zhou, Xiaoqiang Zhu, Kun Gai

We name it COLD (Computing power cost-aware Online and Lightweight Deep pre-ranking system).

Recommendation Systems

Weak Supervision and Referring Attention for Temporal-Textual Association Learning

no code implementations21 Jun 2020 Zhiyuan Fang, Shu Kong, Zhe Wang, Charless Fowlkes, Yezhou Yang

The referring attention is our designed mechanism acting as a scoring function for grounding the given queries over frames temporally.


Gradient Free Minimax Optimization: Variance Reduction and Faster Convergence

no code implementations16 Jun 2020 Tengyu Xu, Zhe Wang, Yingbin Liang, H. Vincent Poor

In this paper, we focus on such a gradient-free setting, and consider the nonconvex-strongly-concave minimax stochastic optimization problem.

Stochastic Optimization

ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization

1 code implementation12 Jun 2020 Xunpeng Huang, Runxin Xu, Hao Zhou, Zhe Wang, Zhengyang Liu, Lei LI

Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence.

BIG-bench Machine Learning Stochastic Optimization

Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

no code implementations12 Jun 2020 Xunpeng Huang, Hao Zhou, Runxin Xu, Zhe Wang, Lei LI

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency.

ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language

2 code implementations ECCV 2020 Zhe Wang, Zhiyuan Fang, Jun Wang, Yezhou Yang

Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions.

Contrastive Learning Person Search +1

Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms

no code implementations7 May 2020 Tengyu Xu, Zhe Wang, Yingbin Liang

In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established.

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

no code implementations NeurIPS 2020 Tengyu Xu, Zhe Wang, Yingbin Liang

We show that the overall sample complexity for a mini-batch AC to attain an $\epsilon$-accurate stationary point improves the best known sample complexity of AC by an order of $\mathcal{O}(\epsilon^{-1}\log(1/\epsilon))$, and the overall sample complexity for a mini-batch NAC to attain an $\epsilon$-accurate globally optimal point improves the existing sample complexity of NAC by an order of $\mathcal{O}(\epsilon^{-1}/\log(1/\epsilon))$.

Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge

1 code implementation24 Apr 2020 Arshdeep Sekhon, Zhe Wang, Yanjun Qi

Learning the differential statistical dependency network between two contexts is essential for many real-life applications, mostly in the high dimensional low sample regime.

Structured Prediction

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching

no code implementations CVPR 2021 Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi

Compared to previous methods for adaptive stereo matching, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.

Domain Adaptation Stereo Matching

Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation

no code implementations7 Apr 2020 Zhe Wang, Daeyun Shin, Charless C. Fowlkes

Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets.

 Ranked #1 on 3D Human Pose Estimation on Surreal (using extra training data)

Monocular 3D Human Pose Estimation

Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization

no code implementations26 Feb 2020 Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh

Our APG-restart is designed to 1) allow for adopting flexible parameter restart schemes that cover many existing ones; 2) have a global sub-linear convergence rate in nonconvex and nonsmooth optimization; and 3) have guaranteed convergence to a critical point and have various types of asymptotic convergence rates depending on the parameterization of local geometry in nonconvex and nonsmooth optimization.

Hierarchical Transformer Network for Utterance-level Emotion Recognition

no code implementations18 Feb 2020 QingBiao Li, CHUNHUA WU, KangFeng Zheng, Zhe Wang

To address these problems, we propose a hierarchical transformer framework (apart from the description of other studies, the "transformer" in this paper usually refers to the encoder part of the transformer) with a lower-level transformer to model the word-level input and an upper-level transformer to capture the context of utterance-level embeddings.

Emotion Recognition in Conversation text-classification

Reanalysis of Variance Reduced Temporal Difference Learning

no code implementations ICLR 2020 Tengyu Xu, Zhe Wang, Yi Zhou, Yingbin Liang

Furthermore, the variance error (for both i. i. d.\ and Markovian sampling) and the bias error (for Markovian sampling) of VRTD are significantly reduced by the batch size of variance reduction in comparison to those of vanilla TD.

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

6 code implementations CVPR 2020 Shaoshuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.

3D Object Detection object-detection

SpiderBoost and Momentum: Faster Variance Reduction Algorithms

no code implementations NeurIPS 2019 Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh

SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization.

Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow

no code implementations28 Nov 2019 Mingyu Ding, Zhe Wang, Bolei Zhou, Jianping Shi, Zhiwu Lu, Ping Luo

Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference.

Optical Flow Estimation Semantic Segmentation +2

Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization

no code implementations27 Oct 2019 Kaiyi Ji, Zhe Wang, Yi Zhou, Yingbin Liang

Two types of zeroth-order stochastic algorithms have recently been designed for nonconvex optimization respectively based on the first-order techniques SVRG and SARAH/SPIDER.

History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms

no code implementations ICML 2020 Kaiyi Ji, Zhe Wang, Bowen Weng, Yi Zhou, Wei zhang, Yingbin Liang

In this paper, we propose a novel scheme, which eliminates backtracking line search but still exploits the information along optimization path by adapting the batch size via history stochastic gradients.

RiWalk: Fast Structural Node Embedding via Role Identification

1 code implementation15 Oct 2019 Xuewei Ma, Geng Qin, Zhiyang Qiu, Mingxin Zheng, Zhe Wang

Learning latent representations for the roles of nodes helps to understand the network and to transfer knowledge across networks.

Feature Engineering General Classification +3

Acutum: When Generalization Meets Adaptability

no code implementations25 Sep 2019 Xunpeng Huang, Zhengyang Liu, Zhe Wang, Yue Yu, Lei LI

To the best of our knowledge, Acutum is the first adaptive gradient method without second moments.

BIG-bench Machine Learning

Towards Effective 2-bit Quantization: Pareto-optimal Bit Allocation for Deep CNNs Compression

no code implementations25 Sep 2019 Zhe Wang, Jie Lin, Mohamed M. Sabry Aly, Sean I Young, Vijay Chandrasekhar, Bernd Girod

In this paper, we address an important problem of how to optimize the bit allocation of weights and activations for deep CNNs compression.


Variable Population Memetic Search: A Case Study on the Critical Node Problem

no code implementations12 Sep 2019 Yangming Zhou, Jin-Kao Hao, Zhang-Hua Fu, Zhe Wang, Xiangjing Lai

Population-based memetic algorithms have been successfully applied to solve many difficult combinatorial problems.

Robust Multi-Modality Multi-Object Tracking

1 code implementation ICCV 2019 Wenwei Zhang, Hui Zhou, Shuyang Sun, Zhe Wang, Jianping Shi, Chen Change Loy

Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects.

Association Autonomous Driving +2

FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images

no code implementations28 Jul 2019 Yunhe Gao, Rui Huang, Ming Chen, Zhe Wang, Jincheng Deng, YuanYuan Chen, Yiwei Yang, Jie Zhang, Chanjuan Tao, Hongsheng Li

In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images.

Organ Segmentation

From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

5 code implementations8 Jul 2019 Shaoshuai Shi, Zhe Wang, Jianping Shi, Xiaogang Wang, Hongsheng Li

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications.

3D Object Detection object-detection +1

Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement

no code implementations CVPR 2019 2019 Jinzhan Su, Zhe Wang, Chunyuan Liao, Haibin Ling

In particular, for a given image, our algorithm first estimates its global facial shape through a global regression network (GRegNet) and then using cascaded local refinement networks (LRefNet) to sequentially improve the alignment result.

Face Alignment regression

Coordinate descent full configuration interaction

1 code implementation12 Feb 2019 Zhe Wang, Yingzhou Li, Jianfeng Lu

We develop an efficient algorithm, coordinate descent FCI (CDFCI), for the electronic structure ground state calculation in the configuration interaction framework.

Chemical Physics Computational Physics

Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization

no code implementations7 Feb 2019 Yi Zhou, Zhe Wang, Kaiyi Ji, Yingbin Liang, Vahid Tarokh

In this paper, we develop novel momentum schemes with flexible coefficient settings to accelerate SPIDER for nonconvex and nonsmooth composite optimization, and show that the resulting algorithms achieve the near-optimal gradient oracle complexity for achieving a generalized first-order stationary condition.

Augmenting Model Robustness with Transformation-Invariant Attacks

no code implementations31 Jan 2019 Houpu Yao, Zhe Wang, Guangyu Nie, Yassine Mazboudi, Yezhou Yang, Yi Ren

The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research.

Image Cropping Translation

A^2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes

no code implementations3 Jan 2019 Kui Xu, Zhe Wang, Jiangping Shi, Hongsheng Li, Qiangfeng Cliff Zhang

Constructing of molecular structural models from Cryo-Electron Microscopy (Cryo-EM) density volumes is the critical last step of structure determination by Cryo-EM technologies.

Pose Estimation Translation

SpiderBoost and Momentum: Faster Stochastic Variance Reduction Algorithms

1 code implementation25 Oct 2018 Zhe Wang, Kaiyi Ji, Yi Zhou, Yingbin Liang, Vahid Tarokh

SARAH and SPIDER are two recently developed stochastic variance-reduced algorithms, and SPIDER has been shown to achieve a near-optimal first-order oracle complexity in smooth nonconvex optimization.

Cubic Regularization with Momentum for Nonconvex Optimization

no code implementations9 Oct 2018 Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan

However, such a successful acceleration technique has not yet been proposed for second-order algorithms in nonconvex optimization. In this paper, we apply the momentum scheme to cubic regularized (CR) Newton's method and explore the potential for acceleration.

A Detection and Segmentation Architecture for Skin Lesion Segmentation on Dermoscopy Images

no code implementations11 Sep 2018 Chengyao Qian, Ting Liu, Hao Jiang, Zhe Wang, Pengfei Wang, Mingxin Guan, Biao Sun

This report summarises our method and validation results for the ISIC Challenge 2018 - Skin Lesion Analysis Towards Melanoma Detection - Task 1: Lesion Segmentation.

Lesion Segmentation Skin Lesion Segmentation

Convergence of Cubic Regularization for Nonconvex Optimization under KL Property

no code implementations NeurIPS 2018 Yi Zhou, Zhe Wang, Yingbin Liang

Cubic-regularized Newton's method (CR) is a popular algorithm that guarantees to produce a second-order stationary solution for solving nonconvex optimization problems.

A Note on Inexact Condition for Cubic Regularized Newton's Method

no code implementations22 Aug 2018 Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan

This note considers the inexact cubic-regularized Newton's method (CR), which has been shown in \cite{Cartis2011a} to achieve the same order-level convergence rate to a secondary stationary point as the exact CR \citep{Nesterov2006}.

Pose Guided Human Video Generation

no code implementations ECCV 2018 Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin

Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.

motion prediction Video Generation

Knowledge Compilation in Multi-Agent Epistemic Logics

no code implementations27 Jun 2018 Liangda Fang, Kewen Wang, Zhe Wang, Ximing Wen

Epistemic logics are a primary formalism for multi-agent systems but major reasoning tasks in such epistemic logics are intractable, which impedes applications of multi-agent epistemic logics in automatic planning.

Learnable Histogram: Statistical Context Features for Deep Neural Networks

no code implementations25 Apr 2018 Zhe Wang, Hongsheng Li, Wanli Ouyang, Xiaogang Wang

Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods.

General Classification object-detection +2

Variational Disparity Estimation Framework for Plenoptic Image

1 code implementation18 Apr 2018 Trung-Hieu Tran, Zhe Wang, Sven Simon

This paper presents a computational framework for accurately estimating the disparity map of plenoptic images.

Disparity Estimation

How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks

no code implementations8 Mar 2018 Linli Xu, Liang Jiang, Chuan Qin, Zhe Wang, Dongfang Du

Generating poetry from images is much more challenging than generating poetry from text, since images contain very rich visual information which cannot be described completely using several keywords, and a good poem should convey the image accurately.

Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization

no code implementations20 Feb 2018 Zhe Wang, Yi Zhou, Yingbin Liang, Guanghui Lan

Cubic regularization (CR) is an optimization method with emerging popularity due to its capability to escape saddle points and converge to second-order stationary solutions for nonconvex optimization.

Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering

1 code implementation24 Jan 2018 Zhe Wang, Xiaoyi Liu, Liangjian Chen, Li-Min Wang, Yu Qiao, Xiaohui Xie, Charless Fowlkes

Visual question answering (VQA) is of significant interest due to its potential to be a strong test of image understanding systems and to probe the connection between language and vision.

Multiple-choice POS +3

End-to-End Video Classification with Knowledge Graphs

no code implementations6 Nov 2017 Fang Yuan, Zhe Wang, Jie Lin, Luis Fernando D'Haro, Kim Jung Jae, Zeng Zeng, Vijay Chandrasekhar

In particular, we unify traditional "knowledgeless" machine learning models and knowledge graphs in a novel end-to-end framework.

BIG-bench Machine Learning Classification +4

Video Object Segmentation with Re-identification

3 code implementations1 Aug 2017 Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu, Jianping Shi, Ping Luo, Xiaoou Tang, Chen Change Loy

Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.

Semantic Segmentation Video Object Segmentation +2

Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection

no code implementations14 Jun 2017 Zhe Wang, Yanxin Yin, Jianping Shi, Wei Fang, Hongsheng Li, Xiaogang Wang

We propose a convolution neural network based algorithm for simultaneously diagnosing diabetic retinopathy and highlighting suspicious regions.

Diabetic Retinopathy Detection

Learning Deep Representations for Scene Labeling with Semantic Context Guided Supervision

no code implementations8 Jun 2017 Zhe Wang, Hongsheng Li, Wanli Ouyang, Xiaogang Wang

The experiments show that our proposed method makes deep models learn more discriminative feature representations without increasing model size or complexity.

Scene Labeling

Temporal Segment Networks for Action Recognition in Videos

9 code implementations8 May 2017 Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc van Gool

Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.

Ranked #18 on Action Classification on Moments in Time (Top 5 Accuracy metric)

Action Classification Action Recognition In Videos +2

Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction

2 code implementations18 Apr 2017 Kun Gai, Xiaoqiang Zhu, Han Li, Kai Liu, Zhe Wang

CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.

Click-Through Rate Prediction Feature Engineering

Crafting GBD-Net for Object Detection

1 code implementation8 Oct 2016 Xingyu Zeng, Wanli Ouyang, Junjie Yan, Hongsheng Li, Tong Xiao, Kun Wang, Yu Liu, Yucong Zhou, Bin Yang, Zhe Wang, Hui Zhou, Xiaogang Wang

The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.

object-detection Object Detection

Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images

no code implementations1 Sep 2016 Limin Wang, Zhe Wang, Yu Qiao, Luc van Gool

These newly designed transferring techniques exploit multi-task learning frameworks to incorporate extra knowledge from other networks and additional datasets into the training procedure of event CNNs.

Multi-Task Learning

Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition

1 code implementation1 Sep 2016 Zhe Wang, Li-Min Wang, Yali Wang, Bo-Wen Zhang, Yu Qiao

In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition.

Scene Recognition

Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

19 code implementations2 Aug 2016 Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc van Gool

The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.

Action Classification Action Recognition In Videos +2

CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

1 code implementation2 Aug 2016 Yuanjun Xiong, Li-Min Wang, Zhe Wang, Bo-Wen Zhang, Hang Song, Wei Li, Dahua Lin, Yu Qiao, Luc van Gool, Xiaoou Tang

This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016.

General Classification Video Classification

Better Exploiting OS-CNNs for Better Event Recognition in Images

no code implementations14 Oct 2015 Limin Wang, Zhe Wang, Sheng Guo, Yu Qiao

Event recognition from still images is one of the most important problems for image understanding.

Object Recognition Scene Recognition

Towards Good Practices for Very Deep Two-Stream ConvNets

5 code implementations8 Jul 2015 Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao

However, for action recognition in videos, the improvement of deep convolutional networks is not so evident.

Action Recognition In Videos Data Augmentation +1

Object-Scene Convolutional Neural Networks for Event Recognition in Images

no code implementations2 May 2015 Limin Wang, Zhe Wang, Wenbin Du, Yu Qiao

Meanwhile, we investigate different network architectures for OS-CNN design, and adapt the deep (AlexNet) and very-deep (GoogLeNet) networks to the task of event recognition.

DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

no code implementations11 Sep 2014 Wanli Ouyang, Ping Luo, Xingyu Zeng, Shi Qiu, Yonglong Tian, Hongsheng Li, Shuo Yang, Zhe Wang, Yuanjun Xiong, Chen Qian, Zhenyao Zhu, Ruohui Wang, Chen-Change Loy, Xiaogang Wang, Xiaoou Tang

In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty.

object-detection Object Detection

Acyclicity Notions for Existential Rules and Their Application to Query Answering in Ontologies

no code implementations4 Feb 2014 Bernardo Cuenca Grau, Ian Horrocks, Markus Krötzsch, Clemens Kupke, Despoina Magka, Boris Motik, Zhe Wang

Existential rules are closely related to the Horn fragments of the OWL 2 ontology language; furthermore, several prominent OWL 2 reasoners implement CQ answering by using the chase to materialise all relevant facts.

Cannot find the paper you are looking for? You can Submit a new open access paper.