Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Zhangyang Wang

Zhangyang Wang

Cross-Modal Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop


Apr 11, 2021
Yan Han, Chongyan Chen, Ahmed Tewfik, Benjamin Glicksberg, Ying Ding, Yifan Peng, Zhangyang Wang

* Preprint 
  Access Paper or Ask Questions

A Design Space Study for LISTA and Beyond


Apr 08, 2021
Tianjian Meng, Xiaohan Chen, Yifan Jiang, Zhangyang Wang

Figure 1 for A Design Space Study for LISTA and Beyond
Figure 2 for A Design Space Study for LISTA and Beyond
Figure 3 for A Design Space Study for LISTA and Beyond
Figure 4 for A Design Space Study for LISTA and Beyond
* Published as a conference paper at ICLR 2021 
  Access Paper or Ask Questions

Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data


Apr 07, 2021
Tingyi Wanyan, Jing Zhang, Ying Ding, Ariful Azad, Zhangyang Wang, Benjamin S Glicksberg

Figure 1 for Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
Figure 2 for Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
Figure 3 for Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data
Figure 4 for Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data

  Access Paper or Ask Questions

Contrastive Syn-to-Real Generalization


Apr 06, 2021
Wuyang Chen, Zhiding Yu, Shalini De Mello, Sifei Liu, Jose M. Alvarez, Zhangyang Wang, Anima Anandkumar

Figure 1 for Contrastive Syn-to-Real Generalization
Figure 2 for Contrastive Syn-to-Real Generalization
Figure 3 for Contrastive Syn-to-Real Generalization
Figure 4 for Contrastive Syn-to-Real Generalization
* Accepted in ICLR 2021 
  Access Paper or Ask Questions

The Elastic Lottery Ticket Hypothesis


Mar 30, 2021
Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Jingjing Liu, Zhangyang Wang

Figure 1 for The Elastic Lottery Ticket Hypothesis
Figure 2 for The Elastic Lottery Ticket Hypothesis
Figure 3 for The Elastic Lottery Ticket Hypothesis
Figure 4 for The Elastic Lottery Ticket Hypothesis

  Access Paper or Ask Questions

Learning to Optimize: A Primer and A Benchmark


Mar 23, 2021
Tianlong Chen, Xiaohan Chen, Wuyang Chen, Howard Heaton, Jialin Liu, Zhangyang Wang, Wotao Yin

Figure 1 for Learning to Optimize: A Primer and A Benchmark
Figure 2 for Learning to Optimize: A Primer and A Benchmark
Figure 3 for Learning to Optimize: A Primer and A Benchmark
Figure 4 for Learning to Optimize: A Primer and A Benchmark

  Access Paper or Ask Questions

UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution


Mar 23, 2021
Xingqian Xu, Zhangyang Wang, Humphrey Shi

Figure 1 for UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution
Figure 2 for UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution
Figure 3 for UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution
Figure 4 for UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution

  Access Paper or Ask Questions

Adversarial Feature Augmentation and Normalization for Visual Recognition


Mar 22, 2021
Tianlong Chen, Yu Cheng, Zhe Gan, Jianfeng Wang, Lijuan Wang, Zhangyang Wang, Jingjing Liu

Figure 1 for Adversarial Feature Augmentation and Normalization for Visual Recognition
Figure 2 for Adversarial Feature Augmentation and Normalization for Visual Recognition
Figure 3 for Adversarial Feature Augmentation and Normalization for Visual Recognition
Figure 4 for Adversarial Feature Augmentation and Normalization for Visual Recognition

  Access Paper or Ask Questions

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective


Mar 16, 2021
Wuyang Chen, Xinyu Gong, Zhangyang Wang

Figure 1 for Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Figure 2 for Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Figure 3 for Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Figure 4 for Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
* accepted as ICLR 2021 poster 
  Access Paper or Ask Questions

Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition


Mar 03, 2021
Jiebin Yan, Yu Zhong, Yuming Fang, Zhangyang Wang, Kede Ma

Figure 1 for Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
Figure 2 for Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
Figure 3 for Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
Figure 4 for Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
* 19 pages, 12 figures, 5 tables, accepted by IJCV 
  Access Paper or Ask Questions

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly


Feb 28, 2021
Tianlong Chen, Yu Cheng, Zhe Gan, Jingjing Liu, Zhangyang Wang

Figure 1 for Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly
Figure 2 for Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly
Figure 3 for Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly
Figure 4 for Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly

  Access Paper or Ask Questions

Sandwich Batch Normalization


Feb 22, 2021
Xinyu Gong, Wuyang Chen, Tianlong Chen, Zhangyang Wang

Figure 1 for Sandwich Batch Normalization
Figure 2 for Sandwich Batch Normalization
Figure 3 for Sandwich Batch Normalization
Figure 4 for Sandwich Batch Normalization
* Codes are available at https://github.com/VITA-Group/Sandwich-Batch-Normalization 
  Access Paper or Ask Questions

Weak NAS Predictors Are All You Need


Feb 21, 2021
Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan

Figure 1 for Weak NAS Predictors Are All You Need
Figure 2 for Weak NAS Predictors Are All You Need
Figure 3 for Weak NAS Predictors Are All You Need
Figure 4 for Weak NAS Predictors Are All You Need

  Access Paper or Ask Questions

TransGAN: Two Transformers Can Make One Strong GAN


Feb 16, 2021
Yifan Jiang, Shiyu Chang, Zhangyang Wang

Figure 1 for TransGAN: Two Transformers Can Make One Strong GAN
Figure 2 for TransGAN: Two Transformers Can Make One Strong GAN
Figure 3 for TransGAN: Two Transformers Can Make One Strong GAN
Figure 4 for TransGAN: Two Transformers Can Make One Strong GAN

  Access Paper or Ask Questions

A Unified Lottery Ticket Hypothesis for Graph Neural Networks


Feb 12, 2021
Tianlong Chen, Yongduo Sui, Xuxi Chen, Aston Zhang, Zhangyang Wang

Figure 1 for A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Figure 2 for A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Figure 3 for A Unified Lottery Ticket Hypothesis for Graph Neural Networks
Figure 4 for A Unified Lottery Ticket Hypothesis for Graph Neural Networks

  Access Paper or Ask Questions

On Dynamic Noise Influence in Differentially Private Learning


Jan 19, 2021
Junyuan Hong, Zhangyang Wang, Jiayu Zhou

Figure 1 for On Dynamic Noise Influence in Differentially Private Learning
Figure 2 for On Dynamic Noise Influence in Differentially Private Learning
Figure 3 for On Dynamic Noise Influence in Differentially Private Learning
Figure 4 for On Dynamic Noise Influence in Differentially Private Learning

  Access Paper or Ask Questions

Good Students Play Big Lottery Better


Jan 18, 2021
Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Figure 1 for Good Students Play Big Lottery Better
Figure 2 for Good Students Play Big Lottery Better
Figure 3 for Good Students Play Big Lottery Better
Figure 4 for Good Students Play Big Lottery Better

  Access Paper or Ask Questions

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training


Jan 04, 2021
Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang

Figure 1 for SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
Figure 2 for SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
Figure 3 for SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
Figure 4 for SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
* arXiv admin note: substantial text overlap with arXiv:2005.03403 
  Access Paper or Ask Questions

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets


Dec 31, 2020
Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Zhangyang Wang, Jingjing Liu

Figure 1 for EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Figure 2 for EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Figure 3 for EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Figure 4 for EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

  Access Paper or Ask Questions

Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity


Dec 29, 2020
Jianghao Shen, Sicheng Wang, Zhangyang Wang

Figure 1 for Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity
Figure 2 for Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity
Figure 3 for Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity
* ICDM Workshops 2018: 399-402 
 * ICDM workshop 2018 
  Access Paper or Ask Questions

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training


Dec 24, 2020
Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan Lin

Figure 1 for FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Figure 2 for FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Figure 3 for FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Figure 4 for FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
* Accepted at NeurIPS 2020 
  Access Paper or Ask Questions

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models


Dec 12, 2020
Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang

Figure 1 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Figure 2 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Figure 3 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Figure 4 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

  Access Paper or Ask Questions

Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing


Nov 28, 2020
Junru Wu, Xiang Yu, Buyu Liu, Zhangyang Wang, Manmohan Chandraker

Figure 1 for Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing
Figure 2 for Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing
Figure 3 for Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing
Figure 4 for Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing

  Access Paper or Ask Questions

Graph Contrastive Learning with Augmentations


Nov 11, 2020
Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen

Figure 1 for Graph Contrastive Learning with Augmentations
Figure 2 for Graph Contrastive Learning with Augmentations
Figure 3 for Graph Contrastive Learning with Augmentations
Figure 4 for Graph Contrastive Learning with Augmentations
* Supplementary materials are available at https://yyou1996.github.io/files/neurips2020_graphcl_supplement.pdf. NeurIPS 2020 
  Access Paper or Ask Questions

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free


Nov 10, 2020
Haotao Wang, Tianlong Chen, Shupeng Gui, Ting-Kuei Hu, Ji Liu, Zhangyang Wang

Figure 1 for Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
Figure 2 for Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
Figure 3 for Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
Figure 4 for Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
* NeurIPS 2020 
  Access Paper or Ask Questions

What Does CNN Shift Invariance Look Like? A Visualization Study


Nov 09, 2020
Jake Lee, Junfeng Yang, Zhangyang Wang

Figure 1 for What Does CNN Shift Invariance Look Like? A Visualization Study
Figure 2 for What Does CNN Shift Invariance Look Like? A Visualization Study
Figure 3 for What Does CNN Shift Invariance Look Like? A Visualization Study
Figure 4 for What Does CNN Shift Invariance Look Like? A Visualization Study
* Presented at the 2020 ECCV Workshop on Real-World Computer Vision from Inputs with Limited Quality (RLQ-TOD 2020), Glasgow, Scotland 
  Access Paper or Ask Questions