Metraipolis › archive › dc_948bf20798d7
To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models — arXiv:2609.08367
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08367
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:59:36.100Z
- SHA-256 of the archived text
6c068bc888295b23c901dba5ae516c830ab6e4746f8bc8146b77a9e2248c9119- Stable URL of this page
https://metraipolis.com/documento/dc_948bf20798d7
How to cite
To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models — arXiv:2609.08367 — arXiv (en), https://arxiv.org/abs/2609.08367 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_948bf20798d7 (Metraipolis archive dc_948bf20798d7, sha256 6c068bc888295b23c901dba5ae516c830ab6e4746f8bc8146b77a9e2248c9119)
BibTeX
@misc{dc948bf20798d7,
title = {To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models — arXiv:2609.08367},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08367},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_948bf20798d7; sha256 6c068bc888295b23c901dba5ae516c830ab6e4746f8bc8146b77a9e2248c9119},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08367. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Test-time adaptation (TTA) has emerged as a prominent strategy for adapting vision-language models to distribution shifts during inference. We conduct a per-sample analysis of model predictions before and after adaptation, and observe two failure modes in existing TTA methods that echo previous work. Adaptations are frequently negligible, yielding no change in the model's predictions, and more severely, they can be detrimental by flipping previously correct predictions to incorrect ones. This naturally raises a question: Can we identify and skip such negligible or harmful adaptations? In this work, we introduce a new problem of selective adaptation, which aims to determine whether a given test sample should undergo adaptation or be skipped. To this end, we propose Cross-Augmentation Similarity (CAS), a simple baseline that performs adaptation only when predictions across augmented views exhibit low similarity. Notably, CAS not only preserves but in some cases improves overall accuracy, even when skipping nearly 85% of the adaptation process. We hope other researchers will explore this new direction and surpass the performance of our baseline. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.08367 — 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 2026-10-16T13:39:43.276Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).