Extracting Clean and Balanced Subset for Noisy Long-tailed Classification

arXiv:2404.06795v1 Announce Type: new
Abstract: Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and clean samples. Despite their effectiveness, they may be limited in handling the joint issue effectively in a unified way. In this work, we develop a novel pseudo labeling method using class prototypes from the perspective of distribution matching, which …

abstract aim arxiv class classification cs.lg datasets design distribution issue noise samples solve type world