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 Tongliang Liu

Tongliang Liu

Exploring Set Similarity for Dense Self-supervised Representation Learning


Jul 19, 2021
Zhaoqing Wang, Qiang Li, Guoxin Zhang, Pengfei Wan, Wen Zheng, Nannan Wang, Mingming Gong, Tongliang Liu

Figure 1 for Exploring Set Similarity for Dense Self-supervised Representation Learning
Figure 2 for Exploring Set Similarity for Dense Self-supervised Representation Learning
Figure 3 for Exploring Set Similarity for Dense Self-supervised Representation Learning
Figure 4 for Exploring Set Similarity for Dense Self-supervised Representation Learning
* 14 pages, 9 figures 
  Access Paper or Ask Questions

Kernel Mean Estimation by Marginalized Corrupted Distributions


Jul 10, 2021
Xiaobo Xia, Shuo Shan, Mingming Gong, Nannan Wang, Fei Gao, Haikun Wei, Tongliang Liu

Figure 1 for Kernel Mean Estimation by Marginalized Corrupted Distributions
Figure 2 for Kernel Mean Estimation by Marginalized Corrupted Distributions
Figure 3 for Kernel Mean Estimation by Marginalized Corrupted Distributions
Figure 4 for Kernel Mean Estimation by Marginalized Corrupted Distributions

  Access Paper or Ask Questions

Revisiting Knowledge Distillation: An Inheritance and Exploration Framework


Jul 01, 2021
Zhen Huang, Xu Shen, Jun Xing, Tongliang Liu, Xinmei Tian, Houqiang Li, Bing Deng, Jianqiang Huang, Xian-Sheng Hua

Figure 1 for Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
Figure 2 for Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
Figure 3 for Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
Figure 4 for Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

Understanding and Improving Early Stopping for Learning with Noisy Labels


Jun 30, 2021
Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, Tongliang Liu

Figure 1 for Understanding and Improving Early Stopping for Learning with Noisy Labels
Figure 2 for Understanding and Improving Early Stopping for Learning with Noisy Labels
Figure 3 for Understanding and Improving Early Stopping for Learning with Noisy Labels
Figure 4 for Understanding and Improving Early Stopping for Learning with Noisy Labels
* 19 pages, 5 figures 
  Access Paper or Ask Questions

Probabilistic Margins for Instance Reweighting in Adversarial Training


Jun 15, 2021
Qizhou Wang, Feng Liu, Bo Han, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, Masashi Sugiyama

Figure 1 for Probabilistic Margins for Instance Reweighting in Adversarial Training
Figure 2 for Probabilistic Margins for Instance Reweighting in Adversarial Training
Figure 3 for Probabilistic Margins for Instance Reweighting in Adversarial Training
Figure 4 for Probabilistic Margins for Instance Reweighting in Adversarial Training
* 17 pages, 4 figures 
  Access Paper or Ask Questions

PI-GNN: A Novel Perspective on Semi-Supervised Node Classification against Noisy Labels


Jun 14, 2021
Xuefeng Du, Tian Bian, Yu Rong, Bo Han, Tongliang Liu, Tingyang Xu, Wenbing Huang, Junzhou Huang

Figure 1 for PI-GNN: A Novel Perspective on Semi-Supervised Node Classification against Noisy Labels
Figure 2 for PI-GNN: A Novel Perspective on Semi-Supervised Node Classification against Noisy Labels
Figure 3 for PI-GNN: A Novel Perspective on Semi-Supervised Node Classification against Noisy Labels
Figure 4 for PI-GNN: A Novel Perspective on Semi-Supervised Node Classification against Noisy Labels
* 16 pages, 3 figures 
  Access Paper or Ask Questions

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation


Jun 11, 2021
Haoang Chi, Feng Liu, Wenjing Yang, Long Lan, Tongliang Liu, Bo Han, William K. Cheung, James T. Kwok

Figure 1 for TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
Figure 2 for TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
Figure 3 for TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
Figure 4 for TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

  Access Paper or Ask Questions

KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation


Jun 11, 2021
Chenhong Zhou, Feng Liu, Chen Gong, Tongliang Liu, Bo Han, William Cheung

Figure 1 for KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation
Figure 2 for KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation
Figure 3 for KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation
Figure 4 for KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation

  Access Paper or Ask Questions

Adversarial Robustness through the Lens of Causality


Jun 11, 2021
Yonggang Zhang, Mingming Gong, Tongliang Liu, Gang Niu, Xinmei Tian, Bo Han, Bernhard Schölkopf, Kun Zhang

Figure 1 for Adversarial Robustness through the Lens of Causality
Figure 2 for Adversarial Robustness through the Lens of Causality
Figure 3 for Adversarial Robustness through the Lens of Causality
Figure 4 for Adversarial Robustness through the Lens of Causality

  Access Paper or Ask Questions

Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training


Jun 10, 2021
Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Jun Yu, Xiaoyu Wang, Tongliang Liu

Figure 1 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Figure 2 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Figure 3 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Figure 4 for Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training

  Access Paper or Ask Questions

Towards Defending against Adversarial Examples via Attack-Invariant Features


Jun 09, 2021
Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang, Chunlei Peng, Xinbo Gao

Figure 1 for Towards Defending against Adversarial Examples via Attack-Invariant Features
Figure 2 for Towards Defending against Adversarial Examples via Attack-Invariant Features
Figure 3 for Towards Defending against Adversarial Examples via Attack-Invariant Features
Figure 4 for Towards Defending against Adversarial Examples via Attack-Invariant Features

  Access Paper or Ask Questions

Reliable Adversarial Distillation with Unreliable Teachers


Jun 09, 2021
Jianing Zhu, Jiangchao Yao, Bo Han, Jingfeng Zhang, Tongliang Liu, Gang Niu, Jingren Zhou, Jianliang Xu, Hongxia Yang

Figure 1 for Reliable Adversarial Distillation with Unreliable Teachers
Figure 2 for Reliable Adversarial Distillation with Unreliable Teachers
Figure 3 for Reliable Adversarial Distillation with Unreliable Teachers
Figure 4 for Reliable Adversarial Distillation with Unreliable Teachers

  Access Paper or Ask Questions

Understanding (Generalized) Label Smoothing when Learning with Noisy Labels


Jun 09, 2021
Jiaheng Wei, Hangyu Liu, Tongliang Liu, Gang Niu, Yang Liu

Figure 1 for Understanding (Generalized) Label Smoothing when Learning with Noisy Labels
Figure 2 for Understanding (Generalized) Label Smoothing when Learning with Noisy Labels
Figure 3 for Understanding (Generalized) Label Smoothing when Learning with Noisy Labels
Figure 4 for Understanding (Generalized) Label Smoothing when Learning with Noisy Labels
* Under Review 
  Access Paper or Ask Questions

Understanding (Generalized) Label Smoothing whenLearning with Noisy Labels


Jun 08, 2021
Jiaheng Wei, Hangyu Liu, Tongliang Liu, Gang Niu, Yang Liu

Figure 1 for Understanding (Generalized) Label Smoothing whenLearning with Noisy Labels
Figure 2 for Understanding (Generalized) Label Smoothing whenLearning with Noisy Labels
Figure 3 for Understanding (Generalized) Label Smoothing whenLearning with Noisy Labels
Figure 4 for Understanding (Generalized) Label Smoothing whenLearning with Noisy Labels
* Under Review 
  Access Paper or Ask Questions

Instance Correction for Learning with Open-set Noisy Labels


Jun 01, 2021
Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama

Figure 1 for Instance Correction for Learning with Open-set Noisy Labels
Figure 2 for Instance Correction for Learning with Open-set Noisy Labels
Figure 3 for Instance Correction for Learning with Open-set Noisy Labels
Figure 4 for Instance Correction for Learning with Open-set Noisy Labels

  Access Paper or Ask Questions

Sample Selection with Uncertainty of Losses for Learning with Noisy Labels


Jun 01, 2021
Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Jun Yu, Gang Niu, Masashi Sugiyama

Figure 1 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Figure 2 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Figure 3 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Figure 4 for Sample Selection with Uncertainty of Losses for Learning with Noisy Labels

  Access Paper or Ask Questions

NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?


May 31, 2021
Jingfeng Zhang, Xilie Xu, Bo Han, Tongliang Liu, Gang Niu, Lizhen Cui, Masashi Sugiyama

Figure 1 for NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?
Figure 2 for NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?
Figure 3 for NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?
Figure 4 for NoiLIn: Do Noisy Labels Always Hurt Adversarial Training?

  Access Paper or Ask Questions

Estimating Instance-dependent Label-noise Transition Matrix using DNNs


May 27, 2021
Shuo Yang, Erkun Yang, Bo Han, Yang Liu, Min Xu, Gang Niu, Tongliang Liu

Figure 1 for Estimating Instance-dependent Label-noise Transition Matrix using DNNs
Figure 2 for Estimating Instance-dependent Label-noise Transition Matrix using DNNs
Figure 3 for Estimating Instance-dependent Label-noise Transition Matrix using DNNs
Figure 4 for Estimating Instance-dependent Label-noise Transition Matrix using DNNs

  Access Paper or Ask Questions

Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition


Apr 22, 2021
Lie Ju, Xin Wang, Lin Wang, Tongliang Liu, Xin Zhao, Tom Drummond, Dwarikanath Mahapatra, Zongyuan Ge

Figure 1 for Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
Figure 2 for Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
Figure 3 for Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
Figure 4 for Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition

  Access Paper or Ask Questions

Removing Adversarial Noise in Class Activation Feature Space


Apr 19, 2021
Dawei Zhou, Nannan Wang, Chunlei Peng, Xinbo Gao, Xiaoyu Wang, Jun Yu, Tongliang Liu

Figure 1 for Removing Adversarial Noise in Class Activation Feature Space
Figure 2 for Removing Adversarial Noise in Class Activation Feature Space
Figure 3 for Removing Adversarial Noise in Class Activation Feature Space
Figure 4 for Removing Adversarial Noise in Class Activation Feature Space

  Access Paper or Ask Questions

Learning with Group Noise


Mar 17, 2021
Qizhou Wang, Jiangchao Yao, Chen Gong, Tongliang Liu, Mingming Gong, Hongxia Yang, Bo Han

Figure 1 for Learning with Group Noise
Figure 2 for Learning with Group Noise
Figure 3 for Learning with Group Noise
Figure 4 for Learning with Group Noise

  Access Paper or Ask Questions

A Machine Learning Approach for Predicting Human Preference for Graph Layouts


Mar 01, 2021
Shijun Cai, Seok-Hee Hong, Jialiang Shen, Tongliang Liu

Figure 1 for A Machine Learning Approach for Predicting Human Preference for Graph Layouts
Figure 2 for A Machine Learning Approach for Predicting Human Preference for Graph Layouts
Figure 3 for A Machine Learning Approach for Predicting Human Preference for Graph Layouts
Figure 4 for A Machine Learning Approach for Predicting Human Preference for Graph Layouts
* 9 pages, 9 figures, PacificVis_Notes 
  Access Paper or Ask Questions

Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation


Feb 28, 2021
Lie Ju, Xin Wang, Lin Wang, Dwarikanath Mahapatra, Xin Zhao, Mehrtash Harandi, Tom Drummond, Tongliang Liu, Zongyuan Ge

Figure 1 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
Figure 2 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
Figure 3 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
Figure 4 for Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation

  Access Paper or Ask Questions

Meta Discovery: Learning to Discover Novel Classes given Very Limited Data


Feb 18, 2021
Haoang Chi, Feng Liu, Wenjing Yang, Long Lan, Tongliang Liu, Gang Niu, Bo Han

Figure 1 for Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
Figure 2 for Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
Figure 3 for Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
Figure 4 for Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

  Access Paper or Ask Questions

Understanding the Interaction of Adversarial Training with Noisy Labels


Feb 09, 2021
Jianing Zhu, Jingfeng Zhang, Bo Han, Tongliang Liu, Gang Niu, Hongxia Yang, Mohan Kankanhalli, Masashi Sugiyama

Figure 1 for Understanding the Interaction of Adversarial Training with Noisy Labels
Figure 2 for Understanding the Interaction of Adversarial Training with Noisy Labels
Figure 3 for Understanding the Interaction of Adversarial Training with Noisy Labels
Figure 4 for Understanding the Interaction of Adversarial Training with Noisy Labels

  Access Paper or Ask Questions

Learning Diverse-Structured Networks for Adversarial Robustness


Feb 08, 2021
Xuefeng Du, Jingfeng Zhang, Bo Han, Tongliang Liu, Yu Rong, Gang Niu, Junzhou Huang, Masashi Sugiyama

Figure 1 for Learning Diverse-Structured Networks for Adversarial Robustness
Figure 2 for Learning Diverse-Structured Networks for Adversarial Robustness
Figure 3 for Learning Diverse-Structured Networks for Adversarial Robustness
Figure 4 for Learning Diverse-Structured Networks for Adversarial Robustness
* 26 pages, 8 figures 
  Access Paper or Ask Questions

Provably End-to-end Label-Noise Learning without Anchor Points


Feb 04, 2021
Xuefeng Li, Tongliang Liu, Bo Han, Gang Niu, Masashi Sugiyama

Figure 1 for Provably End-to-end Label-Noise Learning without Anchor Points
Figure 2 for Provably End-to-end Label-Noise Learning without Anchor Points
Figure 3 for Provably End-to-end Label-Noise Learning without Anchor Points
Figure 4 for Provably End-to-end Label-Noise Learning without Anchor Points

  Access Paper or Ask Questions

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model


Jan 14, 2021
Qizhou Wang, Bo Han, Tongliang Liu, Gang Niu, Jian Yang, Chen Gong

Figure 1 for Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Figure 2 for Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Figure 3 for Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Figure 4 for Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

  Access Paper or Ask Questions