{"ID":2891901,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16753","arxiv_id":"2507.16753","title":"CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation","abstract":"Cross-Domain Few-Shot Segmentation (CD-FSS) remains challenging due to limited data and domain shifts. Recent foundation models like the Segment Anything Model (SAM) have shown remarkable zero-shot generalization capability in general segmentation tasks, making it a promising solution for few-shot scenarios. However, adapting SAM to CD-FSS faces two critical challenges: reliance on manual prompt and limited cross-domain ability. Therefore, we propose the Composable Meta-Prompt (CMP) framework that introduces three key modules: (i) the Reference Complement and Transformation (RCT) module for semantic expansion, (ii) the Composable Meta-Prompt Generation (CMPG) module for automated meta-prompt synthesis, and (iii) the Frequency-Aware Interaction (FAI) module for domain discrepancy mitigation. Evaluations across four cross-domain datasets demonstrate CMP's state-of-the-art performance, achieving 71.8\\% and 74.5\\% mIoU in 1-shot and 5-shot scenarios respectively.","short_abstract":"Cross-Domain Few-Shot Segmentation (CD-FSS) remains challenging due to limited data and domain shifts. Recent foundation models like the Segment Anything Model (SAM) have shown remarkable zero-shot generalization capability in general segmentation tasks, making it a promising solution for few-shot scenarios. However, a...","url_abs":"https://arxiv.org/abs/2507.16753","url_pdf":"https://arxiv.org/pdf/2507.16753v1","authors":"[\"Shuai Chen\",\"Fanman Meng\",\"Chunjin Yang\",\"Haoran Wei\",\"Chenhao Wu\",\"Qingbo Wu\",\"Hongliang Li\"]","published":"2025-07-22T16:42:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}