De-Confusing Pseudo-Labels in Source-Free Domain Adaptation

arXiv:2401.01650v2 Announce Type: replace
Abstract: Source-free domain adaptation (SFDA) aims to adapt a source-trained model to an unlabeled target domain without access to the source data. SFDA has attracted growing attention in recent years, where existing approaches focus on self-training that usually includes pseudo-labeling techniques. In this paper, we introduce a novel noise-learning approach tailored to address noise distribution in domain adaptation settings and learn to de-confuse the pseudo-labels. More specifically, we learn a noise transition matrix of the pseudo-labels …

abstract adapt arxiv attention cs.cv data domain domain adaptation focus free labeling labels noise novel paper self-training source data training type