Metraipolis › archive › dc_2128ff90a8a1
RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation — arXiv:2610.06932
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.06932
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:06:50.483Z
- SHA-256 of the archived text
25bbb78aa7299c8cad5d41994fd453cdabd6a9cc36b81324e2a80babfd8de000- Stable URL of this page
https://metraipolis.com/documento/dc_2128ff90a8a1
How to cite
RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation — arXiv:2610.06932 — arXiv (en), https://arxiv.org/abs/2610.06932 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2128ff90a8a1 (Metraipolis archive dc_2128ff90a8a1, sha256 25bbb78aa7299c8cad5d41994fd453cdabd6a9cc36b81324e2a80babfd8de000)
BibTeX
@misc{dc2128ff90a8a1,
title = {RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation — arXiv:2610.06932},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.06932},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2128ff90a8a1; sha256 25bbb78aa7299c8cad5d41994fd453cdabd6a9cc36b81324e2a80babfd8de000},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06932. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-based cache admission under representation variations. To address these limitations, we propose RADC, which enhances prototype learning through reliable dual caching. RADC introduces a Semantic Foreground Cache that aggregates category-consistent spatial evidence from CLIP representations, yielding foreground prototypes that complement the global cache while mitigating background interference. To reliably manage both caches, Gaussian Risk Admission models multi-view representations as diagonal Gaussian distributions and jointly considers class separation and feature uncertainty to prioritize reliable cache candidates. RADC integrates zero-shot logits with complementary global- and foreground-cache predictions for robust inference. Extensive experiments on cross-domain and out-of-distribution benchmarks demonstrate consistent state-of-the-art performance. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.06932 — 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 2026-10-07T12:37:32.825Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).