Pairwise Similarity Distribution Clustering for Noisy Label Learning

arXiv:2404.01853v1 Announce Type: new
Abstract: Noisy label learning aims to train deep neural networks using a large amount of samples with noisy labels, whose main challenge comes from how to deal with the inaccurate supervision caused by wrong labels. Existing works either take the label correction or sample selection paradigm to involve more samples with accurate labels into the training process. In this paper, we propose a simple yet effective sample selection algorithm, termed as Pairwise Similarity Distribution Clustering~(PSDC), to …

abstract arxiv challenge clustering cs.cv cs.lg deal distribution labels networks neural networks paradigm sample samples supervision train type