{"ID":2871026,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12105","arxiv_id":"2509.12105","title":"FS-SAM2: Adapting Segment Anything Model 2 for Few-Shot Semantic Segmentation via Low-Rank Adaptation","abstract":"Few-shot semantic segmentation has recently attracted great attention. The goal is to develop a model capable of segmenting unseen classes using only a few annotated samples. Most existing approaches adapt a pre-trained model by training from scratch an additional module. Achieving optimal performance with these approaches requires extensive training on large-scale datasets. The Segment Anything Model 2 (SAM2) is a foundational model for zero-shot image and video segmentation with a modular design. In this paper, we propose a Few-Shot segmentation method based on SAM2 (FS-SAM2), where SAM2's video capabilities are directly repurposed for the few-shot task. Moreover, we apply a Low-Rank Adaptation (LoRA) to the original modules in order to handle the diverse images typically found in standard datasets, unlike the temporally connected frames used in SAM2's pre-training. With this approach, only a small number of parameters is meta-trained, which effectively adapts SAM2 while benefiting from its impressive segmentation performance. Our method supports any K-shot configuration. We evaluate FS-SAM2 on the PASCAL-5$^i$, COCO-20$^i$ and FSS-1000 datasets, achieving remarkable results and demonstrating excellent computational efficiency during inference. Code is available at https://github.com/fornib/FS-SAM2","short_abstract":"Few-shot semantic segmentation has recently attracted great attention. The goal is to develop a model capable of segmenting unseen classes using only a few annotated samples. Most existing approaches adapt a pre-trained model by training from scratch an additional module. Achieving optimal performance with these approa...","url_abs":"https://arxiv.org/abs/2509.12105","url_pdf":"https://arxiv.org/pdf/2509.12105v1","authors":"[\"Bernardo Forni\",\"Gabriele Lombardi\",\"Federico Pozzi\",\"Mirco Planamente\"]","published":"2025-09-15T16:32:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":609821,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871026,"paper_url":"https://arxiv.org/abs/2509.12105","paper_title":"FS-SAM2: Adapting Segment Anything Model 2 for Few-Shot Semantic Segmentation via Low-Rank Adaptation","repo_url":"https://github.com/fornib/FS-SAM2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}