Timezone: »

 
Poster
Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization
De Cheng · Yixiong Ning · Nannan Wang · Xinbo Gao · Heng Yang · Yuxuan Du · Bo Han · Tongliang Liu

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #919
in Poster Session 2 »

In label-noise learning, estimating the transition matrix plays an important role in building statistically consistent classifier. Current state-of-the-art consistent estimator for the transition matrix has been developed under the newly proposed sufficiently scattered assumption, through incorporating the minimum volume constraint of the transition matrix T into label-noise learning. To compute the volume of T, it heavily relies on the estimated noisy class posterior. However, the estimation error of the noisy class posterior could usually be large as deep learning methods tend to easily overfit the noisy labels. Then, directly minimizing the volume of such obtained T could lead the transition matrix to be poorly estimated. Therefore, how to reduce the side-effects of the inaccurate noisy class posterior has become the bottleneck of such method. In this paper, we creatively propose to estimate the transition matrix under the forward-backward cycle-consistency regularization, of which we have greatly reduced the dependency of estimating the transition matrix T on the noisy class posterior. We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution. Extensive experimental results consistently justify the effectiveness of the proposed method, on reducing the estimation error of the transition matrix and greatly boosting the classification performance.

Keywords: Transition Matrix · Label-Noise Learning
[ Paper]  [ Slides]  [ Poster]  [ OpenReview] 

Author Information

De Cheng (Xidian University)
Yixiong Ning (Xidian University)
Nannan Wang (Xidian University)
Xinbo Gao (Chongqing University of Post and Telecommunications)

Xinbo Gao received the B.Eng., M.Sc. and Ph.D. degrees in electronic engineering, signal and information processing from Xidian University, Xi'an, China, in 1994, 1997, and 1999, respectively. From 1997 to 1998, he was a research fellow at the Department of Computer Science, Shizuoka University, Shizuoka, Japan. From 2000 to 2001, he was a post-doctoral research fellow at the Department of Information Engineering, the Chinese University of Hong Kong, Hong Kong. Since 2001, he has been at the School of Electronic Engineering, Xidian University. He is a Cheung Kong Professor of Ministry of Education of P. R. China, a Professor of Pattern Recognition and Intelligent System of Xidian University. Since 2020, he has been also a Professor of Computer Science and Technology of Chongqing University of Posts and Telecommunications. His current research interests include image processing, computer vision, multimedia analysis, machine learning and pattern recognition. He has published seven books and around 300 technical articles in refereed journals and proceedings. Prof. Gao is on the Editorial Boards of several journals, including Signal Processing (Elsevier) and Neurocomputing (Elsevier). He served as the General Chair/Co-Chair, Program Committee Chair/Co-Chair, or PC Member for around 30 major international conferences. He is a Fellow of the Institute of Engineering and Technology, a Fellow of the Chinese Institute of Electronics, a Fellow of the China Computer Federation, and Fellow of the Chinese Association for Artificial Intelligence.

Heng Yang (University of Cambridge)
Yuxuan Du (JD explore Academy)
Bo Han (HKBU / RIKEN)
Tongliang Liu (The University of Sydney)

More from the Same Authors