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

TL;DR

This paper introduces CMP, a novel framework that enhances SAM's cross-domain few-shot segmentation by automating prompt generation and mitigating domain shifts, leading to state-of-the-art results across multiple datasets.

Contribution

The paper proposes a composable meta-prompt framework with three modules to improve SAM's adaptability in cross-domain few-shot segmentation tasks.

Findings

Achieves 71.8% mIoU in 1-shot and 74.5% in 5-shot scenarios.

Outperforms existing methods on four cross-domain datasets.

Introduces automated prompt synthesis and domain discrepancy mitigation.

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.