Improving the Instance-Dependent Transition Matrix Estimation by Exploiting Self-Supervised Learning
Lin, Yexiong Yao, Yu Wang, Zhaoqing Shen, Xu Yu, Jun Han, Bo Liu, Tongliang
Lin, Yexiong
Yao, Yu
Wang, Zhaoqing
Shen, Xu
Yu, Jun
Han, Bo
Liu, Tongliang
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The transition matrix reveals the transition relationship between clean labels and noisy labels. It plays an important role in building statistically consistent classifiers for learning with noisy labels. However, in real-world applications, the transition matrix is usually unknown and has to be estimated. It is a challenging task to accurately estimate the transition matrix which usually depends on the instance. With both instances and noisy labels at hand, the major difficulty of estimating the transition matrix comes from the absence of clean label information. Recent work suggests that self-supervised learning methods can effectively infer clean label information. These methods could even achieve comparable performance with supervised learning on many benchmark datasets but without requiring any labels. Motivated by this, our paper presents a practical approach that harnesses self-supervised learning to extract clean label information, which reduces the estimation error of the instance-dependent transition matrix. By exploiting the estimated transition matrix, the performance of classifiers is improved. Empirical results on different datasets illustrate that our proposed methodology outperforms existing state-of-the-art methods in terms of both classification accuracy and transition matrix estimation.
Citation
Y. Lin et al., "Improving the Instance-Dependent Transition Matrix Estimation by Exploiting Self-Supervised Learning," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2025.3595613
Source
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conference
Keywords
Instance-dependent label errors, Instance-dependent transition matrix estimation, Label-noise learning, Self supervised Learning
Subjects
Source
Publisher
IEEE