Metraipolis › archive › dc_7cee2fd4f5df

Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs — arXiv:2609.10333

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.10333
License (as archived): CC0-1.0
Archived: 2026-10-16T11:00:02.150Z
SHA-256 of the archived text: e01ec1427708f92f00c659a0b40b88e3926903c0fbdefdf750ee4ee95417a842
Stable URL of this page: https://metraipolis.com/documento/dc_7cee2fd4f5df

How to cite

Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs — arXiv:2609.10333 — arXiv (en), https://arxiv.org/abs/2609.10333 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cee2fd4f5df (Metraipolis archive dc_7cee2fd4f5df, sha256 e01ec1427708f92f00c659a0b40b88e3926903c0fbdefdf750ee4ee95417a842)

BibTeX

@misc{dc7cee2fd4f5df,
  title = {Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs — arXiv:2609.10333},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10333},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cee2fd4f5df; sha256 e01ec1427708f92f00c659a0b40b88e3926903c0fbdefdf750ee4ee95417a842},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10333. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Uncertainty estimation for medical vision--language models (VLMs) using conformal prediction has gained increasing attention due to its distribution-free coverage guarantees. However, standard conformal prediction relies on exchangeability between calibration and test data and typically requires a sufficiently large calibration set to obtain reliable coverage. These assumptions are difficult to satisfy in few-shot transfer settings, where only a small labeled support set is available to adapt a pretrained VLM to a new medical task, while an unlabeled query set is used for evaluation. Supervised fine-tuning on the support set changes the model parameters and consequently shifts the nonconformity score distribution, breaking exchangeability between calibration and query samples and leading to unreliable coverage under distribution shift. Existing transductive conformal adaptation methods often preserve validity by avoiding supervised updates. While this helps maintain conformal assumptions, it underutilizes the scarce labeled support data and limits task adaptation, which is the primary objective in few-shot learning. In this setting, conformal prediction should serve as an uncertainty estimation layer that supports the adapted model, rather than preventing adaptation itself. To this end, we propose AlignCP, a framework that reconciles supervised few-shot adaptation with conformal uncertainty estimation under non-exchangeability. AlignCP learns a reweighted calibration distribution that reduces the score-level discrepancy between the labeled support set and the unlabeled query set. By aligning the one-dimensional nonconformity score distributions, AlignCP aims to close the coverage gap induced by adaptation without requiring query labels.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.10333 — 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 2026-10-16T10:02:34.379Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).