发表机构
Huazhong University of Science and Technology（华中科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对跨域少样本语义分割中因域偏移致原型匹配不可靠的问题，提出DAUPNet框架，通过协调特征、概率表示原型及用不确定性调节优化，在四个标准目标域取得较好平均mIoU，为跨域少样本语义分割提供了可靠方法。
AI 中文摘要
跨域少样本语义分割主要被表述为学习域不变表示或改善支持-查询对应关系。然而，大的域偏移仍使原型匹配不可靠。我们提出DAUPNet，一个将跨域原型匹配重新表述为不确定性感知原型区分的统一框架。它先协调层次化支持-查询特征，再概率性表示前景和背景原型，最后用估计的不确定性调节对比优化。在四个标准目标域上，DAUPNet在单样本和五样本设置下分别取得72.6%和76.7%的平均mIoU，证明了该方法的有效性。
英文摘要
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
