Metraipolis › archive › dc_22ffc480436d
Exact Dice Degradation Envelopes for Label-Free Segmentation Update Selection — arXiv:2611.00021
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00021
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:23:27.525Z
- SHA-256 of the archived text
d16fbd8cc4a9e19d54824e723baa1b9a427772485f93668f5f35613b2eb382fe- Stable URL of this page
https://metraipolis.com/documento/dc_22ffc480436d
How to cite
Exact Dice Degradation Envelopes for Label-Free Segmentation Update Selection — arXiv:2611.00021 — arXiv (en), https://arxiv.org/abs/2611.00021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22ffc480436d (Metraipolis archive dc_22ffc480436d, sha256 d16fbd8cc4a9e19d54824e723baa1b9a427772485f93668f5f35613b2eb382fe)
BibTeX
@misc{dc22ffc480436d,
title = {Exact Dice Degradation Envelopes for Label-Free Segmentation Update Selection — arXiv:2611.00021},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00021},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22ffc480436d; sha256 d16fbd8cc4a9e19d54824e723baa1b9a427772485f93668f5f35613b2eb382fe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Test-time segmentation updates can improve an unlabeled input while damaging another. Confidence and transformation consistency can rank candidates, but do not in themselves bound the loss caused by returning a changed mask. We derive the exact largest decrease in binary Dice between a baseline and a candidate, maximized over every possible unknown reference mask on the same pixels. A maximizing reference always lies inside baseline foreground: three observable mask counts reduce the problem to at most four reference-cardinality checks. Accepting an output only when its envelope is below a budget gives a deterministic, per-case Dice degradation limit relative to the baseline. A finite grid of logit interpolations permits partial candidate outputs without extra network forwards. Exhaustive and randomized validation checks 5,026,592 reference masks with no discrepancy. We evaluate six independently trained MK-UNet sources, three seeds per task, on ClinicDB, Massachusetts Buildings and the external Kvasir-SEG cohort, including appearance corruptions. Across 17,808 case-condition-seed evaluations, 0 certificate violations occur in the checked candidate comparisons. At a one-point Dice budget, exact versus loose interpolation changes the returned mask in the following fractions of episodes (ClinicDB: 51.0% versus 38.7%; Buildings: 62.1% versus 53.1%; Kvasir-SEG: 52.3% versus 34.9%). Mean Dice effects and useful-update rejection are reported separately from admissibility. An exploratory oracle-presence-bit ablation examines how weak supervision relaxes the empty-baseline restriction. The envelope quantifies relative mask-change risk; it does not certify anatomical correctness, preserve other metrics, or guarantee adaptation benefit. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Image and Video Processing (eess.IV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.00021 — 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 2026-11-03T11:02:37.737Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).