Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning

arXiv:2405.05714v1 Announce Type: cross
Abstract: In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class …

abstract arxiv class classification classification model classifiers consistent cs.cv cs.lg forms fundamental labels learn matrix part posterior role training transition type