Metraipolis › archive › dc_0730041aa86a

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation — arXiv:2608.03147

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03147
License (as archived)
CC0-1.0
Archived
2026-10-31T12:58:16.737Z
SHA-256 of the archived text
4a654605e1468677c2c31f70108a1b69ba1c5ca9c70df55bdcfbc9b2a4ab5968
Stable URL of this page
https://metraipolis.com/documento/dc_0730041aa86a

How to cite

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation — arXiv:2608.03147 — arXiv (en), https://arxiv.org/abs/2608.03147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0730041aa86a (Metraipolis archive dc_0730041aa86a, sha256 4a654605e1468677c2c31f70108a1b69ba1c5ca9c70df55bdcfbc9b2a4ab5968)
BibTeX
@misc{dc0730041aa86a,
  title = {CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation — arXiv:2608.03147},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03147},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0730041aa86a; sha256 4a654605e1468677c2c31f70108a1b69ba1c5ca9c70df55bdcfbc9b2a4ab5968},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Referring Remote Sensing Image Segmentation (RRSIS) has achieved significant progress through the integration of VLMs and the Segment Anything Model (SAM). However, this progress largely relies on strong pre-trained capabilities, while leaving two fundamental limitations insufficiently addressed: (1) Architectural Weak-Coupling, where the unidirectional flow forces reliance on coarse VLM prompts and wastes SAM's pixel-level structural guidance, causing localization drift; and (2) Object-Centric Semantic Bias, where models overemphasize dominant object semantics while remaining insensitive to spatial reasoning crucial for RRSIS. Motivated by these observations, we propose CROSS, a tightly integrated paradigm for RRSIS. First, we introduce Linguistic-Guided Cascaded Distillation (LGCD) to bridge the architectural gap, which distills SAM's geometric affinities as soft regularizers into VLM intermediate layers, injecting dense structural priors to refine localization. Second, Perspective-Spatial Contrastive Learning (PSCL) imposes cross-anchored constraints by mining mask-filtered deceptive distractors and spatial-linguistic counterfactuals as hard negatives, explicitly shattering semantic shortcuts to enforce genuine logical consistency. Extensive experiments on RRSIS benchmarks demonstrate that CROSS achieves state-of-the-art performance and maintains precise localization even under severe spatial description perturbations, standing as a robust new paradigm for RRSIS.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03147 — 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 2026-10-31T12:45:33.227Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).