Metraipolis › archive › dc_c6ffa37da131

Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation — arXiv:2611.04689

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04689
License (as archived)
CC0-1.0
Archived
2026-11-04T12:30:28.642Z
SHA-256 of the archived text
1fafa63260373b0446e9ad7a36c2af0864d8fd1d5c314748615147c54876b24c
Stable URL of this page
https://metraipolis.com/documento/dc_c6ffa37da131

How to cite

Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation — arXiv:2611.04689 — arXiv (en), https://arxiv.org/abs/2611.04689 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c6ffa37da131 (Metraipolis archive dc_c6ffa37da131, sha256 1fafa63260373b0446e9ad7a36c2af0864d8fd1d5c314748615147c54876b24c)
BibTeX
@misc{dcc6ffa37da131,
  title = {Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation — arXiv:2611.04689},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04689},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c6ffa37da131; sha256 1fafa63260373b0446e9ad7a36c2af0864d8fd1d5c314748615147c54876b24c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04689. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04689 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:26:47.289Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).