Accepted at ICLR 2024 Conference LoRA 업그레이드 버전 저자는 SAM의 한계점을 명시하면서 이를 해결하기 위한 method를 제안함. 이때, 좀 더 efficient하면서 여러 도메인에서 general하게 쓸 수 있는 LoRA 기반의 새로운 PEFT method를 제안 Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model The Segment Anything Model (SAM) stands as a foundational framework for image segmentation. While it exhibits remarkable zero-shot generalization in ..

# Foundation # Medical # Wide sperctrum of tasks Paper : https://arxiv.org/abs/2304.12306 Segment Anything in Medical Images Medical image segmentation is a critical component in clinical practice, facilitating accurate diagnosis, treatment planning, and disease monitoring. However, current methods predominantly rely on customized models, which exhibit limited generality across arxiv.org Code : ..

요즘 SAM을 활용한 모델들이 많이 나오는데, medical 영역에서도 많이 시도되고 있는 것 같다. 오늘은 그 중 하나를 리뷰해보려 한다. paper : https://arxiv.org/abs/2306.13731 github : https://github.com/xhu248/AutoSAM/tree/main GitHub - xhu248/AutoSAM: finetuning SAM with non-promptable decoder on medical images finetuning SAM with non-promptable decoder on medical images - GitHub - xhu248/AutoSAM: finetuning SAM with non-promptable decoder on medic..

paper : https://arxiv.org/abs/2304.12620 Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation The Segment Anything Model (SAM) has recently gained popularity in the field of image segmentation. Thanks to its impressive capabilities in all-round segmentation tasks and its prompt-based interface, SAM has sparked intensive discussion within the commun arxiv.org github..