AI RESEARCH
SAIF: A Stability-Aware Inference Framework for Medical Image Segmentation with Segment Anything Model
arXiv CS.CV
•
ArXi:2603.13533v1 Announce Type: new Segment Anything Model (SAM) enable scalable medical image segmentation but suffer from inference-time instability when deployed as a frozen backbone. In practice, bounding-box prompts often contain localization errors, and fixed threshold binarization