Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chae, Joongwon, Luo, Lihui, Yuan, Xi, Yu, Dongmei, Chen, Zhenglin, Zhang, Lian, Qin, Peiwu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918501345656832
author Chae, Joongwon
Luo, Lihui
Yuan, Xi
Yu, Dongmei
Chen, Zhenglin
Zhang, Lian
Qin, Peiwu
author_facet Chae, Joongwon
Luo, Lihui
Yuan, Xi
Yu, Dongmei
Chen, Zhenglin
Zhang, Lian
Qin, Peiwu
contents Accurate tongue segmentation is crucial for reliable TCM analysis. Supervised models require large annotated datasets, while SAM-family models remain prompt-driven. We present Memory-SAM, a training-free, human-prompt-free pipeline that automatically generates effective prompts from a small memory of prior cases via dense DINOv3 features and FAISS retrieval. Given a query image, mask-constrained correspondences to the retrieved exemplar are distilled into foreground/background point prompts that guide SAM2 without manual clicks or model fine-tuning. We evaluate on 600 expert-annotated images (300 controlled, 300 in-the-wild). On the mixed test split, Memory-SAM achieves mIoU 0.9863, surpassing FCN (0.8188) and a detector-to-box SAM baseline (0.1839). On controlled data, ceiling effects above 0.98 make small differences less meaningful given annotation variability, while our method shows clear gains under real-world conditions. Results indicate that retrieval-to-prompt enables data-efficient, robust segmentation of irregular boundaries in tongue imaging. The code is publicly available at https://github.com/jw-chae/memory-sam.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
Chae, Joongwon
Luo, Lihui
Yuan, Xi
Yu, Dongmei
Chen, Zhenglin
Zhang, Lian
Qin, Peiwu
Computer Vision and Pattern Recognition
Accurate tongue segmentation is crucial for reliable TCM analysis. Supervised models require large annotated datasets, while SAM-family models remain prompt-driven. We present Memory-SAM, a training-free, human-prompt-free pipeline that automatically generates effective prompts from a small memory of prior cases via dense DINOv3 features and FAISS retrieval. Given a query image, mask-constrained correspondences to the retrieved exemplar are distilled into foreground/background point prompts that guide SAM2 without manual clicks or model fine-tuning. We evaluate on 600 expert-annotated images (300 controlled, 300 in-the-wild). On the mixed test split, Memory-SAM achieves mIoU 0.9863, surpassing FCN (0.8188) and a detector-to-box SAM baseline (0.1839). On controlled data, ceiling effects above 0.98 make small differences less meaningful given annotation variability, while our method shows clear gains under real-world conditions. Results indicate that retrieval-to-prompt enables data-efficient, robust segmentation of irregular boundaries in tongue imaging. The code is publicly available at https://github.com/jw-chae/memory-sam.
title Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.15849