Metraipolis › archive › dc_377eae790d16

CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation — arXiv:2608.28681

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28681
License (as archived)
CC0-1.0
Archived
2026-10-17T09:53:13.576Z
SHA-256 of the archived text
1b407ce8f6cc67ea8a136959ee425e0db70bf89c8b17c6c5df82a5b8b7c42a50
Stable URL of this page
https://metraipolis.com/documento/dc_377eae790d16

How to cite

CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation — arXiv:2608.28681 — arXiv (en), https://arxiv.org/abs/2608.28681 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_377eae790d16 (Metraipolis archive dc_377eae790d16, sha256 1b407ce8f6cc67ea8a136959ee425e0db70bf89c8b17c6c5df82a5b8b7c42a50)
BibTeX
@misc{dc377eae790d16,
  title = {CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation — arXiv:2608.28681},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28681},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_377eae790d16; sha256 1b407ce8f6cc67ea8a136959ee425e0db70bf89c8b17c6c5df82a5b8b7c42a50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28681. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignment breaks down under domain shift, where artifacts and unseen protocols produce confident errors. Existing post-hoc methods adapt the correction at test time, conditioning on predictive entropy, the logit pattern, or augmentation response, but each proxy is read from the terminal prediction, the very quantity that shift corrupts. This motivates reliability evidence beyond the terminal prediction, which categorical diffusion provides in two ways. First, a generative shape prior keeps a capacity-limited reference intact when appearance is corrupted, so its disagreement with the primary segmentor highlights primary-model errors. Second, every reverse step yields a class distribution, separating persistent disagreement from transient discrepancy. Aggregated over the trajectory, this disagreement correlates with Dice at 0.788, against 0.521 for a matched discriminative control. We therefore propose CARD (Calibration via Agreement in Reverse Diffusion), which maps the temporal aggregate of this disagreement to a temperature field applied per pixel across all classes, so that confidence changes while the segmentation does not. Across cardiac, prostate and brain MRI shifts, CARD lowers calibration error in 45 of 49 comparisons against the strongest baseline in each setting.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28681 — 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 2026-10-17T09:28:47.929Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).