Metraipolis › archive › dc_3c7ccecff382

UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions — arXiv:2609.33996

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33996
License (as archived)
CC0-1.0
Archived
2026-10-07T23:51:48.754Z
SHA-256 of the archived text
6cab3c66eb52ec5460d56978074f93647c76132c4fbdc9c282d68fc153a9bfcc
Stable URL of this page
https://metraipolis.com/documento/dc_3c7ccecff382

How to cite

UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions — arXiv:2609.33996 — arXiv (en), https://arxiv.org/abs/2609.33996 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3c7ccecff382 (Metraipolis archive dc_3c7ccecff382, sha256 6cab3c66eb52ec5460d56978074f93647c76132c4fbdc9c282d68fc153a9bfcc)
BibTeX
@misc{dc3c7ccecff382,
  title = {UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions — arXiv:2609.33996},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33996},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3c7ccecff382; sha256 6cab3c66eb52ec5460d56978074f93647c76132c4fbdc9c282d68fc153a9bfcc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33996. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learned mask refiners improve segmentation accuracy, but it is hard to tell how much of the improvement comes from explicit structure rather than from extra capacity, and whether it holds up when the mask generator or its error distribution changes. UnfoldCRF treats refinement as inference in a conditional random field over pixel labels and latent region variables. Its energy has a corrected unary term, learned local pairwise interactions, and image-conditioned latent-region consistency, with a null state that lets a region with weak label agreement withdraw from the consistency term; inference unrolls damped mean-field updates on this one energy. To isolate the effect of structure, we compare against recurrent black-box refiners that read the same inputs and receive the same parameter budget, stage count, and supervision. On COD10K, UnfoldCRF beats the strongest matched control by 1.0 $F^\omega_\beta$ point, improves all four COD metrics, and lowers the fraction of images made worse from 11.7\% to 8.5\%. Under a train-once protocol over five datasets and several mask sources, the 2.6M-parameter variant gains 4.2 mean $\Delta$IoU against 2.0 for its control, and a variant built on frozen DINOv2 features matches the strongest foundation-model refiner with about a seventh of its resident parameters while staying ahead of its own control. On mask generators never seen in training, the gain is 2.0 $F^\omega_\beta$ points against 0.6 for the control. Zeroing individual messages shows where the corrections come from: the pairwise messages mostly fix boundaries, the region messages mostly fix non-boundary errors. Code and supporting materials will be publicly released.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.33996 — 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 2026-10-07T23:29:27.271Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).