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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Shuai, Meng, Fanman, Yang, Chunjin, Wei, Haoran, Wu, Chenhao, Wu, Qingbo, Li, Hongliang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909699983540224
author Chen, Shuai
Meng, Fanman
Yang, Chunjin
Wei, Haoran
Wu, Chenhao
Wu, Qingbo
Li, Hongliang
author_facet Chen, Shuai
Meng, Fanman
Yang, Chunjin
Wei, Haoran
Wu, Chenhao
Wu, Qingbo
Li, Hongliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation
Chen, Shuai
Meng, Fanman
Yang, Chunjin
Wei, Haoran
Wu, Chenhao
Wu, Qingbo
Li, Hongliang
Computer Vision and Pattern Recognition
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.
title CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.16753