Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation

arXiv:2403.11256v1 Announce Type: new
Abstract: Source-free unsupervised domain adaptation (SFUDA) aims to enable the utilization of a pre-trained source model in an unlabeled target domain without access to source data. Self-training is a way to solve SFUDA, where confident target samples are iteratively selected as pseudo-labeled samples to guide target model learning. However, prior heuristic noisy pseudo-label filtering methods all involve introducing extra models, which are sensitive to model assumptions and may introduce additional errors or mislabeling. In this work, …

arxiv cs.cv domain domain adaptation filtering free type uncertainty unsupervised