Joint Distribution Alignment for Universal Domain Adaptation

arXiv:2608.24429v1 Announce Type: cross 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.

Related

• TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation
• Bridging Day and Night: Unsupervised Cross-Domain Re-Identification with Synergistic Prompt and Prototype Learning
• Unsupervised Domain Adaptation for Sim-to-Real Object Pose Estimation with Contrastive Alignment and Pseudo-Label Refinement
• SoDa2: Single-Stage Open-Set Domain Adaptation via Decoupled Alignment for Cross-Scene Hyperspectral Image Classification

Source: arXiv cs.CV | 2026-08-26