Wasserstein Adversarial Regularization (WAR) on label noise release_wpvodhh46bcg7io3gjrpxv2eum

by Bharath Bhushan Damodaran, Kilian Fatras, Sylvain Lobry, Rémi Flamary, Devis Tuia, Nicolas Courty

Released as a article .

2019  

Abstract

Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we propose a new adversarial regularization scheme based on the Wasserstein distance. Using this distance allows taking into account specific relations between classes by leveraging the geometric properties of the labels space. Our Wasserstein Adversarial Regularization (WAR) encodes a selective regularization, which promotes smoothness of the classifier between some classes, while preserving sufficient complexity of the decision boundary between others. We first discuss how and why adversarial regularization can be used in the context of label noise and then show the effectiveness of our method on five datasets corrupted with noisy labels: in both benchmarks and real datasets, WAR outperforms the state-of-the-art competitors.
In text/plain format

Archived Files and Locations

application/pdf  4.5 MB
file_eo7ofqnppvhzbb6nfr3uoxizlu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-09-26
Version   v2
Language   en ?
arXiv  1904.03936v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bd475fec-2a56-4a39-9937-aebc03a8ce09
API URL: JSON