aiqbench analysis
DAUPNet introduces a novel framework for cross-domain few-shot semantic segmentation by integrating uncertainty modeling into prototype discrimination to handle severe domain shifts. By representing foreground and background prototypes probabilistically rather than deterministically, the method improves robustness in tasks like medical imaging where data scarcity is common. This work advances machine learning techniques specifically designed to maintain accuracy when models encounter significant distributional differences between training and target domains.
DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross-Domain Few-Shot Semantic Segmentation
arXiv:2607.16308v1 Announce Type: cross 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
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 this https URL
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2607.16308 [cs.CV]
(or arXiv:2607.16308v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.16308 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 253 words
Related coverage
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026
Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation
arXiv · Sep 16, 2026
A Candid Abacus AI Review: The All-in-One AI Platform for Professionals & Enterprises
KDnuggets · Sep 10, 2026
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
arXiv · Jun 5, 2026