cs.CVJul 14, 2026

DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross-Domain Few-Shot Semantic Segmentation

Authors: Lei Yuan, Zhongxu Hu, Jingyi Wen, Pengxing Yi

Organizations: Department of Mechanical Science and Engineering, Huazhong University of Science and Technology, China

Abstract

Cross-domain few-shot semantic segmentation (CD-FSS) has predominantly been formulated as learning domain-invariant representations or improving support-query correspondence. Nevertheless, large domain shifts still make prototype matching unreliable: inconsistent hierarchical responses corrupt the support representation, deterministic prototypes cannot express boundary and appearance ambiguity, and treating prototypes with different reliability equally during optimization weakens foreground-background separation. We therefore propose DAUPNet, a unified framework that reformulates cross-domain prototype matching as uncertainty-aware prototype discrimination. DAUPNet first harmonizes hierarchical support-query features to provide stable evidence, then represents foreground and background prototypes probabilistically, and finally uses their estimated uncertainty to regulate contrastive optimization. On four standard target domains, DAUPNet achieves 72.6% and 76.7% average mIoU in the 1-shot and 5-shot settings, respectively, including substantial gains on the two medical domains. These results demonstrate that modeling prototype uncertainty and incorporating it into optimization provides a robust and interpretable approach to CD-FSS under severe domain shift. The code is available at https://github.com/madness-Lei/DAUPNet

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching

    Jun 23, 2026Sujun Sun, Mingwu Ren, Haofeng ZhangFew-Shot LearningCross-Domain Transfer Learning

  2. Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation

    Jun 23, 2026Sujun Sun, Mingwu Ren, Haofeng ZhangPrototype-Based LearningCross-Domain Generalization

  3. Geometry-aware Prototype Learning for Cross-domain Few-shot Medical Image Segmentation

    May 11, 2026Feifan Song, Yuntian Bo, Haofeng ZhangCross-Modality Medical Image SegmentationImage Segmentation