Metraipolis › archive › dc_8a2607c0045d
Lightweight Adaptation of General-Purpose VLMs for Multispectral and SAR Image Understanding — arXiv:2609.02187
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02187
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:55.247Z
- SHA-256 of the archived text
7df3ac0816b808f7acb32f6b3b32b0ed05f101a5075f3cc2ea12e631e4de8387- Stable URL of this page
https://metraipolis.com/documento/dc_8a2607c0045d
How to cite
Lightweight Adaptation of General-Purpose VLMs for Multispectral and SAR Image Understanding — arXiv:2609.02187 — arXiv (en), https://arxiv.org/abs/2609.02187 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a2607c0045d (Metraipolis archive dc_8a2607c0045d, sha256 7df3ac0816b808f7acb32f6b3b32b0ed05f101a5075f3cc2ea12e631e4de8387)
BibTeX
@misc{dc8a2607c0045d,
title = {Lightweight Adaptation of General-Purpose VLMs for Multispectral and SAR Image Understanding — arXiv:2609.02187},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02187},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a2607c0045d; sha256 7df3ac0816b808f7acb32f6b3b32b0ed05f101a5075f3cc2ea12e631e4de8387},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02187. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
General-purpose vision-language models (VLMs) now support strong visual recognition, instruction following, and generation. However, most pretrained visual encoders are built around three-channel natural images and do not directly accommodate observations such as native multispectral measurements or synthetic aperture radar (SAR). Adapting VLMs to these sensors typically requires dedicated encoders and domain pretraining, slowing the reuse of stronger general-purpose checkpoints. We show that the multi-image interface of general-purpose VLMs offers a lightweight alternative. Our protocol renders each observation as five optical views and one SAR view, names them in the prompt, and adapts the language network and selected visual transformer blocks with LoRA. This exposes band composites, spectral indices, and radar backscatter through an existing visual interface. For land-cover recognition, structured supervision couples predicted classes with sensor evidence. We further construct preference pairs in which a true label is omitted while its supporting evidence is retained, encouraging complete predictions that remain consistent with the observations. On a balanced six-class land-cover benchmark derived from BigEarthNet-v2, the adapted Qwen3-VL reaches 0.8275 micro F1. The same input and adaptation protocol improves all four tested VLM architectures and transfers to Sen1Floods11 flood verification and this http URL captioning. Image removal and mismatch controls show that the adapted models use the supplied sensor observations. Together, these results demonstrate that VLMs can be repurposed for multispectral and SAR tasks through rendered inputs and compact LoRA adaptation, without training a new foundation model. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02187 — 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 2026-10-17T05:25:58.076Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).