Metraipolis › archive › dc_56f60f1316dc
On the Relaxation of Conditional Independence Assumption for Image Segmentation — arXiv:2609.38930
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38930
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:44:34.963Z
- SHA-256 of the archived text
6bba5f3c604ff29af59d348ba65dbf167983dc281bb8427db9c3be7622d4bf44- Stable URL of this page
https://metraipolis.com/documento/dc_56f60f1316dc
How to cite
On the Relaxation of Conditional Independence Assumption for Image Segmentation — arXiv:2609.38930 — arXiv (en), https://arxiv.org/abs/2609.38930 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56f60f1316dc (Metraipolis archive dc_56f60f1316dc, sha256 6bba5f3c604ff29af59d348ba65dbf167983dc281bb8427db9c3be7622d4bf44)
BibTeX
@misc{dc56f60f1316dc,
title = {On the Relaxation of Conditional Independence Assumption for Image Segmentation — arXiv:2609.38930},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38930},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56f60f1316dc; sha256 6bba5f3c604ff29af59d348ba65dbf167983dc281bb8427db9c3be7622d4bf44},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38930. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation metrics without modifying model training. Despite its theoretical and empirical success, RankSEG relies on the restrictive Conditional Independence Assumption (CIA), which ignores crucial label correlations and therefore degrades performance in ambiguous or low-contrast scenarios. However, accounting for full label dependence is computationally prohibitive, requiring $\mathcal{O}(d^3)$ time. To address this, we replace the CIA with a Spatially Localized Dependence (SLD) structure that captures local label correlations while keeping the dependence model tractable. We further overcome the remaining computational bottleneck via a Reciprocal Moment Approximation coupled with a novel fixed-point optimization strategy that eliminates exhaustive search. The proposed algorithm achieves a highly practical $\mathcal{O}(d \log d)$ complexity and consistently outperforms conventional argmax and CIA-based RankSEG across diverse segmentation benchmarks. Improvements are significant in low-contrast or small-object scenarios, where label dependence offers valuable signals complementary to image information for accurate segmentation. The code of experiments is available at this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.38930 — 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 2026-10-07T12:14:13.978Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).