Metraipolis › archive › dc_21ff6f819dfa
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement — arXiv:2609.34528
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34528
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:52:14.582Z
- SHA-256 of the archived text
b3ced691fd5972b3e617dae3dcf8e23328c43b8cb20c1a8fba1dd436fa65060c- Stable URL of this page
https://metraipolis.com/documento/dc_21ff6f819dfa
How to cite
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement — arXiv:2609.34528 — arXiv (en), https://arxiv.org/abs/2609.34528 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21ff6f819dfa (Metraipolis archive dc_21ff6f819dfa, sha256 b3ced691fd5972b3e617dae3dcf8e23328c43b8cb20c1a8fba1dd436fa65060c)
BibTeX
@misc{dc21ff6f819dfa,
title = {Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement — arXiv:2609.34528},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34528},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21ff6f819dfa; sha256 b3ced691fd5972b3e617dae3dcf8e23328c43b8cb20c1a8fba1dd436fa65060c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34528. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks. However, OVSS performance often degrades in specialized domains such as medical imaging, remote sensing, and industrial inspection, where dense pixel-level masks for adaptation are costly to obtain and require domain-specific expertise. We propose a preference-guided adaptation framework that replaces dense mask supervision with binary preferences. We observe that different prompt templates produce systematically different segmentations for the same image, a phenomenon we call prompt disagreement, and we repurpose it as a built-in source of preference supervision. Building on this, we mine localized preference queries from regions of high cross-template uncertainty, and adapt the OVSS model with Region-Localized Preference Optimization (RLPO) together with consistency regularization that stabilizes updates outside the queried region. Across extensive experiments on the MESS benchmark, the proposed method achieves consistent gains across diverse OVSS backbones without any pixel-level annotation, and remains effective under noisy preferences. Our code is available at this https URL . 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/2609.34528 — 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 2026-10-07T23:29:27.390Z 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).