cs.LGNov 3, 2026

Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation

Authors: Jinwu Hu, Langyu Bian, Jian Sun, Dongjin Yang, Chao Shuai, Yufeng Wang, Kai Zhou, Bin Xiao, 

Organizations: School of Software Engineering, South China University of Technology, Guangzhou, China · Zhejiang University, Hangzhou, China · School of Future Technology, South China University of Technology, Guangzhou, China · Chongqing University of Posts and Telecommunications, Chongqing, China · 

Abstract

Open-set test-time adaptation (TTA) aims to adapt source-trained models to unlabeled test streams where covariate-shifted in-distribution (csID) samples and covariate-shifted out-of-distribution (csOOD) samples may coexist. Existing TTA methods are typically designed under a closed-set assumption and therefore lack explicit mechanisms for reliably distinguishing csID from csOOD samples. Consequently, csOOD samples may be mistakenly included in confidence-enhancing adaptation, producing harmful gradients that degrade known-class performance. To address this, we propose Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation (UAPA), a plug-and-play method for reliable open-set adaptation. Specifically, we first introduce Uncertainty-Driven ID/OOD Separation, which combines a classifier-prototype score with a mini-batch-normalized evidence-derived uncertainty score to distinguish csID from csOOD samples. We then propose a Dynamic Prototype Refinement strategy that periodically refines class-specific target prototypes using buffered csID features to progressively follow the estimated class directions. Lastly, we introduce Contrastive Prototype Entropy Adaptation, which applies entropy minimization to csID samples and entropy maximization to csOOD samples, while prototype-level contrastive learning aligns csID features with their corresponding target prototypes and reduces the maximum similarity between csOOD features and known-class prototypes. Empirically, UAPA outperforms the strongest baselines on the CIFAR benchmarks and Tiny-ImageNet-C, improving average OSCR by 2.08 and 1.28 percentage points, respectively.

Figures & tables

Explore similar work

CardsList
  1. ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models

    Feb 27, 2026Wei Luo, Yangfan Ou, Jin Deng +4VLM RobustnessTest-Time Adaptation

  2. Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation

    Apr 23, 2026Yingkai Yang, Chaoqi Chen, Hui HuangDomain AdaptationContinual Test-Time Adaptation