GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

arXiv:2403.14410v1 Announce Type: cross
Abstract: Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global …

abstract arxiv clustering cs.ai cs.cv cs.lg domain domain adaptation explore free global networks neural networks paper performance set solution through type universal