File(s) under permanent embargo
Symmetric cross entropy for robust learning with noisy labels
conference contributionposted on 2019-01-01, 00:00 authored by Yisen Wang, Daniel Ma, Zaiyi Chen, Yuan Luo, Jinfeng Yi, James Bailey
Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy labels on some classes ("easy" classes), but more surprisingly, it also suffers from significant under learning on some other classes ("hard" classes). Intuitively, CE requires an extra term to facilitate learning of hard classes, and more importantly, this term should be noise tolerant, so as to avoid overfitting to noisy labels. Inspired by the symmetric KL-divergence, we propose the approach of Symmetric cross entropy Learning (SL), boosting CE symmetrically with a noise robust counterpart Reverse Cross Entropy (RCE). Our proposed SL approach simultaneously addresses both the under learning and overfitting problem of CE in the presence of noisy labels. We provide a theoretical analysis of SL and also empirically show, on a range of benchmark and real-world datasets, that SL outperforms state-of-the-art methods. We also show that SL can be easily incorporated into existing methods in order to further enhance their performance.
EventComputer vision. International conference (2019 : Seoul, South Korea)
Pagination322 - 330
LocationSeoul, South Korea
Place of publicationPiscataway, N.J.
Publication classificationE1.1 Full written paper - refereed
Title of proceedingsICCV 2019 : Proceedings of the IEEE/CVF International Conference on Computer Vision
symmetric cross entropy learningnoise robust counterpart reverse cross entropynoisy labelsrobust learningDNN learningRCEdeep neural networksScience & TechnologyTechnologyComputer Science, Artificial IntelligenceEngineering, Electrical & ElectronicComputer ScienceEngineeringArtificial Intelligence and Image Processing