paper-with-me

홈 › Papers

Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation

2026-04-02 · Wenjie Zhao, Jia Li, Xin Dong, Yapeng Tian, Yu Xiang, Yunhui Guo arxiv

Open-set test-time adaptation (OSTTA) addresses the challenge of adapting models to new environments where out-of-distribution (OOD) samples coexist with in-distribution (ID) samples affected by distribution shifts. In such settings, covariate shift-for example, changes in weather conditions such as snow-can alter ID samples, reducing model reliability. Consequently, models must not only correctly classify covariate-shifted ID (csID) samples but also effectively reject covariate-shifted OOD (csOOD) samples. Entropy minimization is a common strategy in test-time adaptation to maintain ID performance under distribution shifts, while entropy maximization is widely applied to enhance OOD detection. Several studies have sought to combine these objectives to tackle the challenges of OSTTA. However, the intrinsic conflict between entropy minimization and maximization inevitably leads to a trade-off between csID classification and csOOD detection. In this paper, we first analyze the limitations of entropy maximization in OSTTA and then introduce an angular loss to regulate feature norm magnitudes, along with a feature-norm loss to suppress csOOD logits, thereby improving OOD detection. These objectives form ROSETTA, a $\underline{r}$obust $\underline{o}$pen-$\underline{se}$t $\underline{t}$est-$\underline{t}$ime $\underline{a}$daptation. Our method achieves strong OOD detection while maintaining high ID classification performance on CIFAR-10-C, CIFAR-100-C, Tiny-ImageNet-C and ImageNet-C. Furthermore, experiments on the Cityscapes validate the method's effectiveness in real-world semantic segmentation, and results on the HAC dataset demonstrate its applicability across different open-set TTA setups.

📄 PDF Abstract BibTeX arXiv:2604.01589

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SegmentationTest-time Adaptation

Similar Papers 제목 키워드 기반

FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation

2025-08-20 · Gabriel Tjio, Jie Zhang, Xulei Yang, Yun Xing 외 arxiv

Test-time adaptation enables models to adapt to evolving domains. However, balancing the tradeoff between preserving knowledge and adapting to domain shifts remains challenging for model adaptation methods, since adaptin…

Monocular Depth EstimationSemantic SegmentationTest-time AdaptationData Augmentation

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

2026-02-27 · Wei Luo, Yangfan Ou, Jin Deng, Zeshuai Deng 외 arxiv

Large-scale Vision-Language Models (VLMs) exhibit strong zero-shot recognition, yet their real-world deployment is challenged by distribution shifts. While Test-Time Adaptation (TTA) can mitigate this, existing VLM-based…

Test-time Adaptation

A Large Scale Benchmark for Test Time Adaptation Methods in Medical Image Segmentation

2025-12-02 · Wenjing Yu, Shuo Jiang, Yifei Chen, Shuo Chang 외 arxiv

Test time Adaptation is a promising approach for mitigating domain shift in medical image segmentation; however, current evaluations remain limited in terms of modality coverage, task diversity, and methodological consis…

Medical Image SegmentationTest-time Adaptation

Adversarial Reweighting with $α$-Power Maximization for Domain Adaptation

2024-04-26 · Xiang Gu, Xi Yu, Yan Yang, Jian Sun 외

The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a nov…

Domain AdaptationTest-time Adaptation

Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks

2023-12-15 · Pascal Zimmer, Sébastien Andreina, Giorgia Azzurra Marson, Ghassan Karame

Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we…