Metraipolis › archive › dc_c1e1da255fad
DiCoR: Decoupled Referent Disambiguation and Contour Recalibration for Efficient Referring Remote Sensing Image Segmentation — arXiv:2608.12980
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12980
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:55:41.080Z
- SHA-256 of the archived text
2f4d26c09367fd59f6e0ee138723e907a6f3ccca8e844a069393cdcbb27e5f75- Stable URL of this page
https://metraipolis.com/documento/dc_c1e1da255fad
How to cite
DiCoR: Decoupled Referent Disambiguation and Contour Recalibration for Efficient Referring Remote Sensing Image Segmentation — arXiv:2608.12980 — arXiv (en), https://arxiv.org/abs/2608.12980 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c1e1da255fad (Metraipolis archive dc_c1e1da255fad, sha256 2f4d26c09367fd59f6e0ee138723e907a6f3ccca8e844a069393cdcbb27e5f75)
BibTeX
@misc{dcc1e1da255fad,
title = {DiCoR: Decoupled Referent Disambiguation and Contour Recalibration for Efficient Referring Remote Sensing Image Segmentation — arXiv:2608.12980},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12980},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c1e1da255fad; sha256 2f4d26c09367fd59f6e0ee138723e907a6f3ccca8e844a069393cdcbb27e5f75},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12980. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Referring remote sensing image segmentation (RRSIS) aims to delineate targets specified by natural language expressions in remote sensing imagery. Existing methods mainly follow joint fusion segmentation (JFS) or decoupled prompt segmentation (DPS). JFS is efficient but often suffers from limited accuracy because referent localization and mask delineation are optimized under a unified objective, whereas DPS separates localization from mask generation using spatial prompts and foundation segmenters at the cost of higher memory consumption and inference latency. To bridge this gap, we propose DiCoR, a decoupled referent disambiguation and contour recalibration framework built on an efficient JFS pipeline. DiCoR addresses two key challenges: distinguishing the correct referent from ambiguous candidates and refining coarse masks after localization. A disambiguation-aware localization guidance strategy ranks salient candidate regions with adaptive linguistic cues and injects the resulting localization prior into fused features. A lightweight contour recalibration module further predicts residual corrections to coarse logits under localized contour supervision, improving mask quality with limited computational overhead. Experiments on RefSegRS, RRSIS-D, and RISBench show that DiCoR achieves the best segmentation accuracy across all three benchmarks. On RefSegRS, it improves mIoU and gIoU by 4.90% and 2.16% over a competitive JFS method while running 2.4-6.5 times faster than the evaluated DPS method, demonstrating a favorable accuracy-efficiency trade-off. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.12980 — 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 2026-10-19T04:46:30.143Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).