arXiv cs.CV
· Papers
Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
arXiv:2510.15849v3 Announce Type: replace Abstract: 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 effecti