Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications  

作　　者：Wei Ji Jingjing Li Qi Bi Tingwei Liu Wenbo Li Li Cheng 

机构地区：[1]University of Alberta,Edmonton T6G 2R3,Canada [2]Wuhan University,Wuhan 430072,China [3]Dalian University of Technology,Dalian 116024,China [4]Samsung Research America,Mountain View 94043,USA

出　　处：《Machine Intelligence Research》2024年第4期617-630,共14页机器智能研究（英文版）

基　　金：supported by the Mitacs,CFI-JELF and NSERC Discovery grants.

摘　　要：Recently,Meta AI Research approaches a general,promptable segment anything model(SAM)pre-trained on an unprecedentedly large segmentation dataset(SA-1B).Without a doubt,the emergence of SAM will yield significant benefits for a wide array of practical image segmentation applications.In this study,we conduct a series of intriguing investigations into the performance of SAM across various applications,particularly in the fields of natural images,agriculture,manufacturing,remote sensing and healthcare.We analyze and discuss the benefits and limitations of SAM,while also presenting an outlook on its future development in segmentation tasks.By doing so,we aim to give a comprehensive understanding of SAM's practical applications.This work is expected to provide insights that facilitate future research activities toward generic segmentation.Source code is publicly available at https://github.com/LiuTingWed/SAM-Not-Perfect.

关 键 词：Segment anything model(SAM) visual perception segmentation foundational model computer vision. 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]