Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels

Authors

  • Pengfei Chen The Chinese University of Hong Kong
  • Junjie Ye VIVO AI Lab
  • Guangyong Chen Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Jingwei Zhao VIVO AI Lab
  • Pheng-Ann Heng The Chinese University of Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

DOI:

https://doi.org/10.1609/aaai.v35i13.17364

Keywords:

Safety, Robustness & Trustworthiness

Abstract

For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essential aspects: training and validation, with which we address critical issues in learning with noisy labels. For training, we show that maximizing training accuracy on sufficiently many noisy samples yields an approximately optimal classifier. For validation, we prove that a noisy validation set is reliable, addressing the critical demand of model selection in scenarios like hyperparameter-tuning and early stopping. Previously, model selection using noisy validation samples has not been theoretically justified. We verify our theoretical results and additional claims with extensive experiments. We show characterizations of models trained with noisy labels, motivated by our theoretical results, and verify the utility of a noisy validation set by showing the impressive performance of a framework termed noisy best teacher and student (NTS). Our code is released.

Downloads

Published

2021-05-18

How to Cite

Chen, P., Ye, J., Chen, G., Zhao, J., & Heng, P.-A. (2021). Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11451-11461. https://doi.org/10.1609/aaai.v35i13.17364

Issue

Section

AAAI Technical Track on Philosophy and Ethics of AI