Hsin-Hung Cho

Efficient Medical Segmentation Anything Model for Robust Lightweight Segmentation under Imperfect Data in Embedded Healthcare.

This paper replaces the SAM image encoder with an Efficient Vision Transformer (EfficientViT) backbone and introduces offline knowledge distillation to transfer domain-aware feature representations from the Medical Segment Anything Model (MedSAM) to a compact student network, demonstrating stable performance under imperfect inputs and inexact supervision.