Metraipolis › archive › dc_3ccc81bab643

Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter? — arXiv:2609.23967

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23967
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:39.554Z
SHA-256 of the archived text
2a303d75c6cc766fc6f89e4e8ea8e1c54e0fd5dc7e34a86ea32645e45855f78e
Stable URL of this page
https://metraipolis.com/documento/dc_3ccc81bab643

How to cite

Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter? — arXiv:2609.23967 — arXiv (en), https://arxiv.org/abs/2609.23967 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ccc81bab643 (Metraipolis archive dc_3ccc81bab643, sha256 2a303d75c6cc766fc6f89e4e8ea8e1c54e0fd5dc7e34a86ea32645e45855f78e)
BibTeX
@misc{dc3ccc81bab643,
  title = {Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter? — arXiv:2609.23967},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23967},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ccc81bab643; sha256 2a303d75c6cc766fc6f89e4e8ea8e1c54e0fd5dc7e34a86ea32645e45855f78e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23967. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models are increasingly adapted from generation to conditional prediction, where a conditioning signal is combined with an evolving noisy representation of the target. In fully supervised segmentation, however, the conditioning image can already support direct target prediction, so endpoint performance alone establishes neither reliance on the added diffusion state nor a deterministic advantage over image-only prediction. For state reliance, we disrupt target-derived state content or correct image-state pairing during retraining of twelve published methods across three datasets, with ten matched seeds per setting. All 40 original-method comparisons whose evaluated-mask routes remained downstream of noised-quantity reconstruction exhibited state reliance, whereas all 30 comparisons with a segmentation-supervised bypass preserved reference performance. Rerouting five originally bypass-capable methods by forcing segmentation supervision through noise-to-mask reconstruction converted all 30 corresponding comparisons from preserved performance to state reliance. For deterministic utility, matched image-only counterparts achieved similar or better performance in 28 of 35 settings overall, including 16 of 20 whose native methods relied on both audited state properties. These results identify supervision path as a determinant of state reliance in the audited methods. Separately, matched image-only counterparts show that diffusion-specific computation often provides no deterministic endpoint advantage, including in methods that rely on the audited state properties. More generally, when conditioning already supports strong target prediction, diffusion-specific claims require additional evidence that the added state is used and that diffusion-specific computation improves the claimed capability beyond a matched condition-only counterpart.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.23967 — 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 2026-10-09T06:58:09.613Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).