Towards Robust Uncertainty Estimation in the Presence of Noisy Labels

Pan，Chao1,2; Yuan，Bo1,2; Zhou，Wei3; Yao，Xin1,2

10.1007/978-3-031-15919-0_56

2022

31st International Conference on Artificial Neural Networks (ICANN)

0302-9743

1611-3349

978-3-031-15918-3

LECT NOTES ARTIF INT

13529 LNCS

673-684

SEP 06-09, 2022

Univ W England,Bristol,ENGLAND

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

In security-critical applications, it is essential to know how confident the model is in its predictions. Many uncertainty estimation methods have been proposed recently, and these methods are reliable when the training data do not contain labeling errors. However, we find that the quality of these uncertainty estimation methods decreases dramatically when noisy labels are present in the training data. In some datasets, the uncertainty estimates would become completely absurd, even though these labeling noises barely affect the test accuracy. We further analyze the impact of existing label noise handling methods on the reliability of uncertainty estimates, although most of these methods focus only on improving the accuracy of the models. We identify that the data cleaning-based approach can alleviate the influence of label noise on uncertainty estimates to some extent, but there are still some drawbacks. Finally, we propose a robust uncertainty estimation method under label noise. Compared with other algorithms, our approach achieves a more reliable uncertainty estimates in the presence of noisy labels, especially when there are large-scale labeling errors in the training data.

Mis-classification detection Noisy label Out-of-distribution data Uncertainty estimation

First ; Corresponding

English

CPCI-S

Guangdong Provincial Key Laboratory[2020B121201001]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:000866210600056

2-s2.0-85138766849

Scopus

1.Research Institute of Trustworthy Autonomous System,Southern University of Science and Technology (SUSTech),Shenzhen,518055,China
2.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Southern University of Science and Technology (SUSTech),Shenzhen,518055,China
3.Trustworthiness Theory Research Center,Huawei Technology Co.,Ltd.,Shenzhen,China

Pan，Chao,Yuan，Bo,Zhou，Wei,et al. Towards Robust Uncertainty Estimation in the Presence of Noisy Labels[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:673-684.