用可组合元提示让SAM模型在少样本跨域分割中表现更优
CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation
- 设计可自动合成提示的元提示框架，解决人工提示依赖问题
- 1次和5次示例下达到71.8%和74.5%的mIoU，性能领先
- 适合做少样本分割且需跨域泛化的研究者参考
跨域少样本分割（CD-FSS）因数据有限和域偏移仍具挑战性。近期基础模型如分段一切模型（SAM）在通用分割任务中展现出出色的零样本泛化能力，为少样本场景提供潜在解决方案。然而将SAM应用于CD-FSS面临两大难题：依赖人工提示与跨域能力不足。为此，我们提出可组合元提示（CMP）框架，包含三个关键模块：(i) 参考补全与转换（RCT）模块实现语义扩展，(ii) 可组合元提示生成（CMPG）模块实现自动化元提示合成，(iii) 频率感知交互（FAI）模块缓解域差异。在四个跨域数据集上的评估表明，CMP达到当前最优性能，在1次示例和5次示例场景下分别获得71.8%和74.5%的mIoU。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。