SAMDA: Leveraging SAM on Few-Shot Domain Adaptation for Electronic Microscopy Segmentation

arXiv:2403.07951v1 Announce Type: cross
Abstract: It has been shown that traditional deep learning methods for electronic microscopy segmentation usually suffer from low transferability when samples and annotations are limited, while large-scale vision foundation models are more robust when transferring between different domains but facing sub-optimal improvement under fine-tuning. In this work, we present a new few-shot domain adaptation framework SAMDA, which combines the Segment Anything Model(SAM) with nnUNet in the embedding space to achieve high transferability and accuracy. Specifically, we …

abstract annotations arxiv cs.cv cs.lg deep learning domain domain adaptation domains eess.iv electronic few-shot fine-tuning foundation improvement low microscopy robust sam samples scale segmentation type vision