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

DevFeed: [DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross-Domain Few-Shot Semantic Segmentation](<https://devfeed.tech/articles/daupnet-domain-aware-uncertainty-modeling-for-reliable-prototype-discrimination-in-cross-domain-few-shot-semantic-segmentation-111907.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.16308>)

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

Published: 2026-11-02T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [few-shot](<https://devfeed.tech/topics/few-shot.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [background](<https://devfeed.tech/tags/background.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [cd](<https://devfeed.tech/tags/cd.md>), [code](<https://devfeed.tech/tags/code.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [discrimination](<https://devfeed.tech/tags/discrimination.md>), [domain](<https://devfeed.tech/tags/domain.md>), [domains](<https://devfeed.tech/tags/domains.md>), [express](<https://devfeed.tech/tags/express.md>), [features](<https://devfeed.tech/tags/features.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [first](<https://devfeed.tech/tags/first.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

## AI overview

DAUPNet addresses unreliable prototype matching in cross-domain few-shot semantic segmentation by harmonizing hierarchical support-query features, representing foreground and background prototypes probabilistically, and using estimated uncertainty to regulate contrastive optimization. The abstract reports average mIoU of 72.6% in 1-shot and 76.7% in 5-shot evaluation across four standard target domains, with substantial gains on two medical domains. These findings are presented as evidence that uncertainty-aware prototype discrimination can improve robustness under severe domain shift.

## Source excerpt

arXiv:2607.16308v2 Announce Type: replace-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