Metraipolis › archive › dc_0a677f3e19cd

FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation — arXiv:2609.03384

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03384
License (as archived)
CC0-1.0
Archived
2026-10-17T02:56:15.553Z
SHA-256 of the archived text
ddca6f1f08a5234f0d4fe556932b792f84fa0d84909e9e781e9e963af7ae40a3
Stable URL of this page
https://metraipolis.com/documento/dc_0a677f3e19cd

How to cite

FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation — arXiv:2609.03384 — arXiv (en), https://arxiv.org/abs/2609.03384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0a677f3e19cd (Metraipolis archive dc_0a677f3e19cd, sha256 ddca6f1f08a5234f0d4fe556932b792f84fa0d84909e9e781e9e963af7ae40a3)
BibTeX
@misc{dc0a677f3e19cd,
  title = {FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation — arXiv:2609.03384},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03384},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0a677f3e19cd; sha256 ddca6f1f08a5234f0d4fe556932b792f84fa0d84909e9e781e9e963af7ae40a3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In-Context Segmentation (ICS) aims to precisely segment arbitrary semantic concepts, such as objects or parts, given one or a few annotated visual exemplars. In this paper, we revisit ICS from a more classical segmentation perspective, viewing it as a coarse-to-fine progressive refinement process. Rather than directly predicting the final mask through reference-query matching, we progressively refine the segmentation from coarse and ambiguous foreground responses to precise and complete foreground structures. Building upon this perspective, we propose a training-free in-context segmentation framework, termed FoRIS. Specifically, FoRIS consists of three key stages: Foreground Purification, Foreground Localization, and Foreground Consolidation, which progressively suppress background distractions, localize discriminative target regions, and recover complete foreground structures through semantic aggregation. Experimental results demonstrate that FoRIS achieves SOTA performance across semantic and part segmentation tasks, with average improvements of 4.5 and 4.8 mIoU points over existing approaches in the 1-shot and 5-shot settings, respectively. Code: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.03384 — 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 2026-10-17T02:27:18.954Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).