Learning class predication distributions with noisy labels

Qihao Zhao; Yan Nie; Wei Hu; Fan Zhang

doi:10.1117/12.2623597

16 February 2022 Learning class predication distributions with noisy labels

Qihao Zhao, Yan Nie, Wei Hu, Fan Zhang

Proceedings Volume 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021); 1208309 (2022) https://doi.org/10.1117/12.2623597
Event: Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 2021, Kunming, China

Abstract

In this paper, we propose a simple but very effective approach in the presence of noisy labels. The memorization effects of Deep Neural Networks (DNNs) manifests that they first memorize training data with clean labels and memorize data with noisy labels gradually. Based on this phenomenon, we build Class Prediction Distributions(CPD) for each sample in the initial stage of network training. On the basis of CPD, we use our clean data selection strategy to divide training data into confidently clean data and noisy data. In this selection strategy, we rank the maximum value of CPD. Top-ranked samples are more likely to be clean samples. Finally, noisy labels classification is successfully achieved by using semi-supervised learning. Experiments on benchmark datasets including MNIST, Cifar-10, Cifar-100 and Clothing1M demonstrate that our approach can achieve a competitive performance.

Citation Download Citation

Qihao Zhao, Yan Nie, Wei Hu, and Fan Zhang "Learning class predication distributions with noisy labels", Proc. SPIE 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 1208309 (16 February 2022); https://doi.org/10.1117/12.2623597

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available