Search Results for author: Zhe Wang

Found 192 papers, 75 papers with code

Simplified and Generalized Masked Diffusion for Discrete Data

no code implementations6 Jun 2024 Jiaxin Shi, Kehang Han, Zhe Wang, Arnaud Doucet, Michalis K. Titsias

In this work, we aim to provide a simple and general framework that unlocks the full potential of masked diffusion models.

Language Modelling

Hybrid-Field Channel Estimation for XL-MIMO Systems with Stochastic Gradient Pursuit Algorithm

no code implementations24 May 2024 Hao Lei, Jiayi Zhang, Zhe Wang, Bo Ai, Derrick Wing Kwan Ng

For the first scenario in which the prior knowledge of the specific proportion of the number of near-field and far-field channel paths is known, the scheme can effectively leverage the angular-domain sparsity of the far-field channels and the polar-domain sparsity of the near-field channels such that the channel estimation in these two fields can be performed separately.

AccidentBlip2: Accident Detection With Multi-View MotionBlip2

1 code implementation18 Apr 2024 Yihua Shao, Hongyi Cai, Xinwei Long, Weiyi Lang, Zhe Wang, Haoran Wu, Yan Wang, Jiayi Yin, Yang Yang, Yisheng Lv, Zhen Lei

The inference capabilities of neural networks using cameras limit the accuracy of accident detection in complex transportation systems.

Language Modelling Large Language Model +2

Decision Transformer for Wireless Communications: A New Paradigm of Resource Management

no code implementations8 Apr 2024 Jie Zhang, Jun Li, Long Shi, Zhe Wang, Shi Jin, Wen Chen, H. Vincent Poor

By leveraging the power of DT models learned over extensive datasets, the proposed architecture is expected to achieve rapid convergence with many fewer training epochs and higher performance in a new context, e. g., similar tasks with different state and action spaces, compared with DRL.

Edge-computing Management +1

Attention Calibration for Disentangled Text-to-Image Personalization

1 code implementation CVPR 2024 Yanbing Zhang, Mengping Yang, Qin Zhou, Zhe Wang

However, an intriguing problem persists: Is it possible to capture multiple, novel concepts from one single reference image?

Image Generation Novel Concepts

SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection

no code implementations12 Mar 2024 Hongcheng Zhang, Liu Liang, Pengxin Zeng, Xiao Song, Zhe Wang

Sparse 3D detectors have received significant attention since the query-based paradigm embraces low latency without explicit dense BEV feature construction.

3D Object Detection object-detection

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

no code implementations CVPR 2024 Xingyi Li, Zhiguo Cao, Yizheng Wu, Kewei Wang, Ke Xian, Zhe Wang, Guosheng Lin

To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields.

Style Transfer

StaPep: an open-source tool for the structure prediction and feature extraction of hydrocarbon-stapled peptides

1 code implementation28 Feb 2024 Zhe Wang, Jianping Wu, Mengjun Zheng, Chenchen Geng, Borui Zhen, Wei zhang, Hui Wu, Zhengyang Xu, Gang Xu, Si Chen, Xiang Li

Many tools exist for extracting structural and physiochemical descriptors from linear peptides to predict their properties, but similar tools for hydrocarbon-stapled peptides are lacking. Here, we present StaPep, a Python-based toolkit designed for generating 2D/3D structures and calculating 21 distinct features for hydrocarbon-stapled peptides. The current version supports hydrocarbon-stapled peptides containing 2 non-standard amino acids (norleucine and 2-aminoisobutyric acid) and 6 nonnatural anchoring residues (S3, S5, S8, R3, R5 and R8). Then we established a hand-curated dataset of 201 hydrocarbon-stapled peptides and 384 linear peptides with sequence information and experimental membrane permeability, to showcase StaPep's application in artificial intelligence projects. A machine learning-based predictor utilizing above calculated features was developed with AUC of 0. 85, for identifying cell-penetrating hydrocarbon-stapled peptides. StaPep's pipeline spans data retrieval, cleaning, structure generation, molecular feature calculation, and machine learning model construction for hydrocarbon-stapled peptides. The source codes and dataset are freely available on Github: https://github. com/dahuilangda/stapep_package.


EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

2 code implementations23 Feb 2024 Zhe Wang, Siqi Fan, Xiaoliang Huo, Tongda Xu, Yan Wang, Jingjing Liu, Yilun Chen, Ya-Qin Zhang

In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.

3D Object Detection Autonomous Driving +2

Idempotence and Perceptual Image Compression

1 code implementation17 Jan 2024 Tongda Xu, Ziran Zhu, Dailan He, Yanghao Li, Lina Guo, Yuanyuan Wang, Zhe Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang

However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec.

Image Compression

AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction

no code implementations9 Dec 2023 Qi Liu, Xuyang Hou, Defu Lian, Zhe Wang, Haoran Jin, Jia Cheng, Jun Lei

Most existing methods focus on the network architecture design of the CTR model for better accuracy and suffer from the data sparsity problem.

Click-Through Rate Prediction Collaborative Filtering +2

Magicoder: Empowering Code Generation with OSS-Instruct

1 code implementation4 Dec 2023 Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, Lingming Zhang

Magicoder models are trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets to generate diverse instruction data for code.

Code Generation Text-to-Code Generation

ESTformer: Transformer Utilizing Spatiotemporal Dependencies for EEG Super-resolution

no code implementations3 Dec 2023 Dongdong Li, Zhongliang Zeng, Zhe Wang, Hai Yang

The ESTformer, with the fixed masking strategy, adopts a mask token to up-sample the low-resolution (LR) EEG data in case of disturbance from mathematical interpolation methods.

EEG Emotion Recognition +3

EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction on Mobile Devices

no code implementations16 Nov 2023 Jingnan Gao, Zhuo Chen, Yichao Yan, Bowen Pan, Zhe Wang, Jiangjing Lyu, Xiaokang Yang

In our method, we first employ an efficient surface-based model with a multi-view supervision module to ensure accurate mesh reconstruction.

3D Reconstruction Surface Reconstruction

Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction

no code implementations15 Nov 2023 Qi Liu, Xuyang Hou, Haoran Jin, Jin Chen, Zhe Wang, Defu Lian, Tan Qu, Jia Cheng, Jun Lei

The insights from this subset reveal the user's decision-making process related to the candidate item, improving prediction accuracy.

Click-Through Rate Prediction

Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior

1 code implementation17 Oct 2023 Ruibo Li, Chi Zhang, Zhe Wang, Chunhua Shen, Guosheng Lin

By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to generate its pseudo flow labels.

Motion Estimation motion prediction +2

Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation

1 code implementation30 Aug 2023 Mengping Yang, Zhe Wang, Wenyi Feng, Qian Zhang, Ting Xiao

Furthermore, the frequency awareness of the model is reinforced by encouraging the model to distinguish frequency signals.

Image Generation

Interactive segmentation in aerial images: a new benchmark and an open access web-based tool

no code implementations25 Aug 2023 Zhe Wang, Shoukun Sun, Xiang Que, Xiaogang Ma

Compared to existing interactive segmentation tools, RSISeg offers robust interactivity, modifiability, and adaptability to remote sensing data.

Interactive Segmentation Land Cover Classification +2

Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks

2 code implementations ICCV 2023 Kaixin Xu, Zhe Wang, Xue Geng, Jie Lin, Min Wu, XiaoLi Li, Weisi Lin

On ImageNet, we achieve up to 4. 7% and 4. 6% higher top-1 accuracy compared to other methods for VGG-16 and ResNet-50, respectively.

Combinatorial Optimization

Conditional Perceptual Quality Preserving Image Compression

no code implementations16 Aug 2023 Tongda Xu, Qian Zhang, Yanghao Li, Dailan He, Zhe Wang, Yuanyuan Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang

We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information.

Image Compression

Phased Deep Spatio-temporal Learning for Highway Traffic Volume Prediction

no code implementations11 Aug 2023 Weilong Ding, Tianpu Zhang, Zhe Wang

Inter-city highway transportation is significant for citizens' modern urban life and generates heterogeneous sensory data with spatio-temporal characteristics.

Image Synthesis under Limited Data: A Survey and Taxonomy

1 code implementation31 Jul 2023 Mengping Yang, Zhe Wang

Despite numerous efforts to enhance training stability and synthesis quality in the limited data scenarios, there is a lack of a systematic survey that provides 1) a clear problem definition, critical challenges, and taxonomy of various tasks; 2) an in-depth analysis on the pros, cons, and remain limitations of existing literature; as well as 3) a thorough discussion on the potential applications and future directions in the field of image synthesis under limited data.

Image Generation Memorization

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

1 code implementation28 Jun 2023 Haihao Shen, Hengyu Meng, Bo Dong, Zhe Wang, Ofir Zafrir, Yi Ding, Yu Luo, Hanwen Chang, Qun Gao, Ziheng Wang, Guy Boudoukh, Moshe Wasserblat

We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large.

Model Compression

Federated Learning-based Vehicle Trajectory Prediction against Cyberattacks

1 code implementation14 Jun 2023 Zhe Wang, Tingkai Yan

With the development of the Internet of Vehicles (IoV), vehicle wireless communication poses serious cybersecurity challenges.

Federated Learning Trajectory Prediction

Multi-Scale And Token Mergence: Make Your ViT More Efficient

no code implementations8 Jun 2023 Zhe Bian, Zhe Wang, Wenqiang Han, Kangping Wang

To tackle these issues, we propose a novel token pruning method that retains information from non-crucial tokens by merging them with more crucial tokens, thereby mitigating the impact of pruning on model performance.

Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit

1 code implementation8 Jun 2023 Xinhang Li, Yiying Yang, Zheng Yuan, Zhe Wang, Qinwen Wang, Chen Xu, Lei LI, Jianhua He, Lin Zhang

For the more challenging problem of pursuing multiple evading vehicles, these algorithms typically select a fixed target evading vehicle for pursuing vehicles without considering dynamic traffic situation, which significantly reduces pursuing success rate.

Multi-agent Reinforcement Learning reinforcement-learning

COPR: Consistency-Oriented Pre-Ranking for Online Advertising

no code implementations6 Jun 2023 Zhishan Zhao, Jingyue Gao, Yu Zhang, Shuguang Han, Siyuan Lou, Xiang-Rong Sheng, Zhe Wang, Han Zhu, Yuning Jiang, Jian Xu, Bo Zheng

In this architecture, the pre-ranking model is expected to be a lightweight approximation of the ranking model, which handles more candidates with strict latency requirements.

Graph Analysis Using a GPU-based Parallel Algorithm: Quantum Clustering

no code implementations24 May 2023 Zhe Wang, ZhiJie He, Ding Liu

The article introduces a new method for applying Quantum Clustering to graph structures.


A Lightweight Domain Adversarial Neural Network Based on Knowledge Distillation for EEG-based Cross-subject Emotion Recognition

no code implementations12 May 2023 Zhe Wang, Yongxiong Wang, Jiapeng Zhang, Yiheng Tang, Zhiqun Pan

The domain adversarial neural networks (DANN), where the classification loss and domain loss jointly update the parameters of feature extractor, are adopted to deal with the domain shift.

EEG Emotion Recognition +1

Blockchained Federated Learning for Internet of Things: A Comprehensive Survey

no code implementations8 May 2023 Yanna Jiang, Baihe Ma, Xu Wang, Ping Yu, Guangsheng Yu, Zhe Wang, Wei Ni, Ren Ping Liu

The demand for intelligent industries and smart services based on big data is rising rapidly with the increasing digitization and intelligence of the modern world.

Federated Learning Management

PGrad: Learning Principal Gradients For Domain Generalization

1 code implementation2 May 2023 Zhe Wang, Jake Grigsby, Yanjun Qi

In this work, we develop a novel DG training strategy, we call PGrad, to learn a robust gradient direction, improving models' generalization ability on unseen domains.

Domain Generalization

Transformer with Selective Shuffled Position Embedding and Key-Patch Exchange Strategy for Early Detection of Knee Osteoarthritis

no code implementations17 Apr 2023 Zhe Wang, Aladine Chetouani, Mohamed Jarraya, Didier Hans, Rachid Jennane

In this paper, we propose a novel approach based on the Vision Transformer (ViT) model with original Selective Shuffled Position Embedding (SSPE) and key-patch exchange strategies to obtain different input sequences as a method of data augmentation for early detection of KOA (KL-0 vs KL-2).

Data Augmentation Position +1

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

1 code implementation CVPR 2024 Jihan Yang, Runyu Ding, Weipeng Deng, Zhe Wang, Xiaojuan Qi

We propose a lightweight and scalable Regional Point-Language Contrastive learning framework, namely \textbf{RegionPLC}, for open-world 3D scene understanding, aiming to identify and recognize open-set objects and categories.

Contrastive Learning Instance Segmentation +2

A Confident Labelling Strategy Based on Deep Learning for Improving Early Detection of Knee OsteoArthritis

no code implementations23 Mar 2023 Zhe Wang, Aladine Chetouani, Rachid Jennane

Knee OsteoArthritis (KOA) is a prevalent musculoskeletal disorder that causes decreased mobility in seniors.

VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection

2 code implementations20 Mar 2023 Zhe Wang, Siqi Fan, Xiaoliang Huo, Tongda Xu, Yan Wang, Jingjing Liu, Yilun Chen, Ya-Qin Zhang

In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint.

3D Object Detection Autonomous Driving +2

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 in challenging lighting conditions.

Data Augmentation Segmentation +2

Calibration-free BEV Representation for Infrastructure Perception

1 code implementation7 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.

3D 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 Decoder +1

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.

Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving

no code implementations CVPR 2023 Ruibo Li, Hanyu Shi, Ziang Fu, Zhe Wang, Guosheng Lin

To this end, we propose a two-stage weakly supervised approach, where the segmentation model trained with the incomplete binary masks in Stage1 will facilitate the self-supervised learning of the motion prediction network in Stage2 by estimating possible moving foregrounds in advance.

Autonomous Driving motion prediction +2

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

1 code implementation CVPR 2023 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 +1

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

1 code implementation27 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 (RL)

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 #17 on 3D Human Pose Estimation on Human3.6M (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.

Generative Adversarial Network 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 Neural Network +2

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 Vocal Bursts Intensity Prediction

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 +3

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

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

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 both market option prices and local volatility using deep neural networks, respectively.

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 #20 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

2 code implementations24 Sep 2021 Jake Grigsby, Zhe Wang, Nam Nguyen, Yanjun Qi

Multivariate time series forecasting focuses on predicting future values based on historical context.

Multivariate Time Series Forecasting Time Series

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 +3

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 +5

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 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.

Dielectric Constant

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 +4

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

8 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 +3

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.

Cloud Computing Management

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 +4

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.

Q-Learning Reinforcement Learning (RL)

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.

Clustering 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

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.

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

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.

Attribute Contrastive Learning +2

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.

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

12 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.

Object object-detection +1

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 Segmentation +3

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

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.


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

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.

Autonomous Driving Multi-Object Tracking +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 Segmentation

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

6 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 +2

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.