Segment Anything Model and Parameter-Efficient Fine-Tuning for Medical Image Analysis
发布时间:2023年06月06日
浏览次数:2188
发布者: Biao Ma
主讲人: 李海凤(BICMR)
活动时间: 从 2023-06-12 15:00 到 16:30
场地: 北京国际数学研究中心,全斋全29教室
Abstract: Powered by large-scale pre-training, the Segment Anything Model (SAM) proposed by Meta AI Research has made significant progress in image segmentation and gained popularity in the field of computer vision. With a growing number of foundation models developed, Parameter-Efficient Fine-Tuning(PEFT)is increasingly exploited as a valuable approach for knowledge transfer from pre-trained foundation models to specific domain tasks. In this talk, we will give an introduction about SAM and PEFT, and then further focus on their applications in medical image analysis.