# CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation

Source: [CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation](<https://www.sota2.com/research/paper/68fa7a231e209131cea81425>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:13:22.731Z

Authors: Shuai Chen, Fanman Meng, Chunjin Yang, Haoran Wei, Chenhao Wu, Qingbo Wu, Hongliang Li

Published: 2025-07-22T16:42:23.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.16753>)

[PDF](<https://arxiv.org/pdf/2507.16753.pdf>)
