Metraipolis › archive › dc_00dad028a79a
Calibrating Multimodal Test-Time Adaptation under Reliability and Availability Modality Shifts — arXiv:2611.03232
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03232
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:55:23.514Z
- SHA-256 of the archived text
7e25402ea6cffb404398e22e0dabddc81bdc78b5d1cb32c7dcb3bff3935316fa- Stable URL of this page
https://metraipolis.com/documento/dc_00dad028a79a
How to cite
Calibrating Multimodal Test-Time Adaptation under Reliability and Availability Modality Shifts — arXiv:2611.03232 — arXiv (en), https://arxiv.org/abs/2611.03232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00dad028a79a (Metraipolis archive dc_00dad028a79a, sha256 7e25402ea6cffb404398e22e0dabddc81bdc78b5d1cb32c7dcb3bff3935316fa)
BibTeX
@misc{dc00dad028a79a,
title = {Calibrating Multimodal Test-Time Adaptation under Reliability and Availability Modality Shifts — arXiv:2611.03232},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03232},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00dad028a79a; sha256 7e25402ea6cffb404398e22e0dabddc81bdc78b5d1cb32c7dcb3bff3935316fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal test-time adaptation (TTA) enables pretrained multimodal models to accommodate distribution shifts during inference using only unlabeled test data, without recourse to the original training data. Compared with unimodal adaptation, multimodal adaptation is further complicated by the coexistence and interaction of multiple representation perspectives. This complexity is particularly pronounced under modality reliability shifts, which preserve modality availability but degrade information quality, and modality availability shifts, which render the corresponding modality entirely inaccessible. Category-conditional Gaussian modeling offers a natural starting point for handling such distributional variations, having proven effective in unimodal test-time adaptation for characterizing representation distributions, yet its extension to multimodal settings requires a more elaborate formulation. To this end, we propose Adaptive Probabilistic Gaussian Calibration (AdaPGC), which extends category-conditional Gaussian modeling across modality-specific and multimodal fusion representations for probabilistic calibration under multimodal distribution shifts. AdaPGC continuously updates category-conditional Gaussian models over modality-specific and fusion representations, using the resulting probabilistic predictions to calibrate source model predictions and guide reliability based rectification, while exploiting their joint distributions to recover unavailable fusion representations. Extensive experiments under diverse modality corruption and missingness conditions demonstrate that AdaPGC effectively improves robustness under both modality reliability and availability shifts. Our source code will be released at this https URL . 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/2611.03232 — 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 2026-11-03T18:16:53.060Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).