Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation

arXiv:2404.10574v1 Announce Type: cross
Abstract: Standard Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target but usually requires simultaneous access to both source and target data. Moreover, UDA approaches commonly assume that source and target domains share the same labels space. Yet, these two assumptions are hardly satisfied in real-world scenarios. This paper considers the more challenging Source-Free Open-set Domain Adaptation (SF-OSDA) setting, where both assumptions are dropped. We propose a novel …

abstract access arxiv class cs.ai cs.cv cs.lg data domain domain adaptation domains free knowledge labels segregation set space standard transfer type uncertainty unsupervised