Metraipolis › archive › dc_79a6ada8d60b
Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation — arXiv:2609.10495
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10495
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T11:00:06.893Z
- SHA-256 of the archived text
07fd48756e260913749d2a0cc47727b22227afe0a42940e4cbf8b647df076638- Stable URL of this page
https://metraipolis.com/documento/dc_79a6ada8d60b
How to cite
Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation — arXiv:2609.10495 — arXiv (en), https://arxiv.org/abs/2609.10495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79a6ada8d60b (Metraipolis archive dc_79a6ada8d60b, sha256 07fd48756e260913749d2a0cc47727b22227afe0a42940e4cbf8b647df076638)
BibTeX
@misc{dc79a6ada8d60b,
title = {Cross-Model Agreement as a Deployment-Time Reliability Signal for Automatic Polyp Segmentation — arXiv:2609.10495},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10495},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79a6ada8d60b; sha256 07fd48756e260913749d2a0cc47727b22227afe0a42940e4cbf8b647df076638},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In real-time colonoscopy, ground-truth annotations are unavailable at inference, so polyp segmentation models can fail silently. We propose Referee-Based Quality Estimation (RBQE), a reference-free framework measuring agreement between a primary segmentation model and an independently trained referee on the same image. RBQE is evaluated on a standardized 1,223-image external benchmark drawn from four public datasets, using four referee configurations chosen to separate two design axes: referee independence and architectural diversity. Using a common Agreement Dice descriptor, a same-architecture referee differing from the primary model only in random initialization already yields a useful reliability signal (ROC-AUC = 0.923), showing that independent training alone is sufficient. Cross-architecture referees improve further: SegFormer-B0 achieves the strongest performance (ROC-AUC = 0.960), significantly outperforming the same-architecture control and UNet++, and exceeding a representative Test-Time Augmentation baseline by 0.055 ROC-AUC under an identical protocol, whereas a prompt-coupled MedSAM referee underperforms despite maximal architectural diversity. Because empty-mask agreement is trivially separable, we also report a restricted evaluation excluding such cases: ROC-AUC falls to 0.876 (SegFormer-B0, 1,046 images) and 0.783 (same-architecture control, 975 images), yet RBQE's margin over both baselines widens on this identical subset. RBQE additionally increases the mean Dice of retained predictions as low-agreement cases are progressively rejected, supporting selective prediction, and requires only one additional deterministic referee forward pass at inference. Our study therefore supports cross-model agreement as a practical, interpretable reliability framework for automated polyp segmentation. 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) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.10495 — 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 2026-10-16T10:02:34.404Z 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).