Metraipolis › archive › dc_7ac87c497433
From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection — arXiv:2609.09876
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09876
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:59:47.675Z
- SHA-256 of the archived text
7cdbdb7d0a073d84a7f7ff7bb42ab91ccb81dbdedc61c2336d58919759585254- Stable URL of this page
https://metraipolis.com/documento/dc_7ac87c497433
How to cite
From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection — arXiv:2609.09876 — arXiv (en), https://arxiv.org/abs/2609.09876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ac87c497433 (Metraipolis archive dc_7ac87c497433, sha256 7cdbdb7d0a073d84a7f7ff7bb42ab91ccb81dbdedc61c2336d58919759585254)
BibTeX
@misc{dc7ac87c497433,
title = {From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection — arXiv:2609.09876},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09876},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ac87c497433; sha256 7cdbdb7d0a073d84a7f7ff7bb42ab91ccb81dbdedc61c2336d58919759585254},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dense change detection in remote sensing requires vision-language models (VLMs) to compare bi-temporal images and generate accurate pixel-level masks. Existing VLMs are largely confined to change captioning outputs, and the few that produce pixel-level masks still rely on external decoders or flat text-as-mask serialization, which are less effective for small and fragmented changes. We introduce QUAKE-CD, a framework that recasts dense change prediction as syntax-verifiable structured generation. QUAKE-CD represents binary change masks as grammar-constrained quadtree token sequences, making the masks compact, syntactically checkable, and deterministically decodable within an autoregressive generation space. We further construct QUAKE-CoT, which pairs these sequences with chain-of-thought traces grounded in visual evidence, and jointly optimizes textual reasoning and spatial dense prediction through a progressive curriculum followed by grammar-gated dual-reward RL. On QUAKE-CoT, QUAKE-CD achieves 78.31% accumulated F1, outperforming decoder-based and flat text-as-mask VLMs while producing more faithful bi-temporal reasoning. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.09876 — 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 2026-10-16T10:02:34.335Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).