Alert button
Picture for Gang Niu

Gang Niu

Alert button

Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks

Nov 01, 2022
Jianan Zhou, Jianing Zhu, Jingfeng Zhang, Tongliang Liu, Gang Niu, Bo Han, Masashi Sugiyama

Figure 1 for Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Figure 2 for Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Figure 3 for Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Figure 4 for Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Viaarxiv icon

FedMT: Federated Learning with Mixed-type Labels

Oct 05, 2022
Qiong Zhang, Aline Talhouk, Gang Niu, Xiaoxiao Li

Figure 1 for FedMT: Federated Learning with Mixed-type Labels
Figure 2 for FedMT: Federated Learning with Mixed-type Labels
Figure 3 for FedMT: Federated Learning with Mixed-type Labels
Figure 4 for FedMT: Federated Learning with Mixed-type Labels
Viaarxiv icon

Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack

Jun 15, 2022
Ruize Gao, Jiongxiao Wang, Kaiwen Zhou, Feng Liu, Binghui Xie, Gang Niu, Bo Han, James Cheng

Viaarxiv icon

Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation

Jun 06, 2022
De Cheng, Tongliang Liu, Yixiong Ning, Nannan Wang, Bo Han, Gang Niu, Xinbo Gao, Masashi Sugiyama

Figure 1 for Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
Figure 2 for Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
Figure 3 for Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
Figure 4 for Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
Viaarxiv icon

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

Apr 07, 2022
Nan Lu, Zhao Wang, Xiaoxiao Li, Gang Niu, Qi Dou, Masashi Sugiyama

Figure 1 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Figure 2 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Figure 3 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Figure 4 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Viaarxiv icon

On the Effectiveness of Adversarial Training against Backdoor Attacks

Feb 22, 2022
Yinghua Gao, Dongxian Wu, Jingfeng Zhang, Guanhao Gan, Shu-Tao Xia, Gang Niu, Masashi Sugiyama

Figure 1 for On the Effectiveness of Adversarial Training against Backdoor Attacks
Figure 2 for On the Effectiveness of Adversarial Training against Backdoor Attacks
Figure 3 for On the Effectiveness of Adversarial Training against Backdoor Attacks
Figure 4 for On the Effectiveness of Adversarial Training against Backdoor Attacks
Viaarxiv icon

Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification

Feb 01, 2022
Takashi Ishida, Ikko Yamane, Nontawat Charoenphakdee, Gang Niu, Masashi Sugiyama

Figure 1 for Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Figure 2 for Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Figure 3 for Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Figure 4 for Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Viaarxiv icon

PiCO: Contrastive Label Disambiguation for Partial Label Learning

Jan 29, 2022
Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao

Figure 1 for PiCO: Contrastive Label Disambiguation for Partial Label Learning
Figure 2 for PiCO: Contrastive Label Disambiguation for Partial Label Learning
Figure 3 for PiCO: Contrastive Label Disambiguation for Partial Label Learning
Figure 4 for PiCO: Contrastive Label Disambiguation for Partial Label Learning
Viaarxiv icon

Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

Oct 22, 2021
Jiaheng Wei, Zhaowei Zhu, Hao Cheng, Tongliang Liu, Gang Niu, Yang Liu

Figure 1 for Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Figure 2 for Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Figure 3 for Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Figure 4 for Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Viaarxiv icon