Joint Distribution Alignment for Universal Domain Adaptation

Researchers propose Joint Distribution Alignment for Universal Domain Adaptation (JAUA), a new algorithm that aligns joint distributions using Chi-Square divergence and a progressive pseudo-labeling method to handle Universal Domain Adaptation (UniDA), where source and target label spaces differ. The study provides an upper bound on generalization error for UniDA and reports that JAUA outperforms existing methods on six public image datasets.

arXiv:2608.24429v1 Announce Type: new Abstract: Unsupervised domain adaptation UDA has been widely concerned in the fields of machine learning, pattern recognition, and computer vision. Traditional UDA learning usually assumes that the label spaces of the source and target domains are exactly the same and only needs to solve the problem of sample distribution drift existing between two domains. However, in real world applications, the label spaces between two domains may be different. In this case, there are both sample distribution drift and class spatial difference between domains, namely Universal Domain Adaptation UniDA learning scenario. At present, existing works rarely offer theoretical analysis for universal domain adaptation. In this paper, we provide an upper bound of the generalization error for universal domain adaptation. According to the proposed generalization error bound, we propose a novel UniDA algorithm called Joint Distribution Alignment for Universal Domain Adaptation JAUA , which aligns the joint distributions by minimizing the distribution discrepancy calculated by Chi-Square divergence. Furthermore, we propose a progressive pseudo-labeling method to assign the pseudo labels to unlabeled target samples. The experiment results on six public image datasets demonstrate the superiority of JAUA in handling the UniDA problem.