Metraipolis › archive › dc_dae4cd25029f
From Visual Matching to Textual Conditioning: Cross-Domain Few-Shot Segmentation via Reference Inversion — arXiv:2611.04084
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04084
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:56:09.003Z
- SHA-256 of the archived text
3b64c7850ae3229695963c285da70991ff0f53364c65a8094d93ed667de01ac6- Stable URL of this page
https://metraipolis.com/documento/dc_dae4cd25029f
How to cite
From Visual Matching to Textual Conditioning: Cross-Domain Few-Shot Segmentation via Reference Inversion — arXiv:2611.04084 — arXiv (en), https://arxiv.org/abs/2611.04084 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dae4cd25029f (Metraipolis archive dc_dae4cd25029f, sha256 3b64c7850ae3229695963c285da70991ff0f53364c65a8094d93ed667de01ac6)
BibTeX
@misc{dcdae4cd25029f,
title = {From Visual Matching to Textual Conditioning: Cross-Domain Few-Shot Segmentation via Reference Inversion — arXiv:2611.04084},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04084},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dae4cd25029f; sha256 3b64c7850ae3229695963c285da70991ff0f53364c65a8094d93ed667de01ac6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04084. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cross-Domain Few-Shot Segmentation (CD-FSS) aims to segment objects from unseen domains using only a few annotated references. Recent Segment Anything Model (SAM)-based methods have advanced CD-FSS, yet their reference-target visual matching is highly sensitive to target appearance variations. SAM3 introduces text-conditioned segmentation, enabling natural-language descriptions to guide segmentation across target images, but directly using the category name as the condition still yields unstable performance under severe domain shifts. We propose Reference Inversion for SAM3 (RI-SAM3) that leverages SAM3's large-scale vision-language pre-training to learn suitable textual tokens for each target category. RI-SAM3 comprises three core designs: (i) Bi-level Reference Inversion that learns complementary tokens before and after the frozen text encoder: the former remain anchored in SAM3's text space while the latter represent the category more flexibly; (ii) Layer-adaptive Textual Conditioning combines these tokens differently as object queries evolve across decoder layers; and (iii) Presence-aware Confidence Supervision that jointly supervises query confidence and target presence for reliable predictions. With SAM3 frozen, RI-SAM3 optimizes around 12K parameters only per category and it efficiently segments each target in a single forward pass with reusable textual conditioning without per-sample reference-target visual matching. Extensive experiments over multiple widely adopted benchmarks show that RI-SAM3 achieves superior performance consistently in CD-FSS tasks, together with strong robustness, efficiency, and generalization. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.04084 — 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 2026-11-04T12:33:47.102Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).