{"ID":2858843,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07135","arxiv_id":"2510.07135","title":"Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models","abstract":"Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However, their ability to generalize in low-data regimes, such as few-shot learning, remains insufficiently explored. In this work, we present the first structured benchmark for evaluating few-shot adaptation methods on RSVLMs. We conduct comprehensive experiments across ten remote sensing scene classification datasets, applying five widely used few-shot adaptation strategies to three state-of-the-art RSVLMs with varying backbones. Our findings reveal that models with similar zero-shot performance can exhibit markedly different behavior under few-shot adaptation, with some RSVLMs being inherently more amenable to such adaptation than others. The variability of performance and the absence of a clear winner among existing methods highlight the need for the development of more robust methods for few-shot adaptation tailored to RS. To facilitate future research, we provide a reproducible benchmarking framework and open-source code to systematically evaluate RSVLMs under few-shot conditions. The source code is publicly available on Github: https://github.com/elkhouryk/fewshot_RSVLMs","short_abstract":"Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However, their ability to generalize in low-data regimes, such as few-shot learning, remains insufficiently explored. In this work, we present the fi...","url_abs":"https://arxiv.org/abs/2510.07135","url_pdf":"https://arxiv.org/pdf/2510.07135v1","authors":"[\"Karim El Khoury\",\"Maxime Zanella\",\"Christophe De Vleeschouwer\",\"Benoit Macq\"]","published":"2025-10-08T15:29:48Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":608592,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2858843,"paper_url":"https://arxiv.org/abs/2510.07135","paper_title":"Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models","repo_url":"https://github.com/elkhouryk/fewshot_RSVLMs","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}