SAM struggles in concealed scenes—empirical study on “Segment Anything”

作     者：Ge-Peng JI Deng-Ping FAN Peng XU Bowen ZHOU Ming-Ming CHENG Luc VAN GOOL Ge-Peng JI;Deng-Ping FAN;Peng XU;Bowen ZHOU;Ming-Ming CHENG;Luc VAN GOOL

作者机构：School of ComputingAustralian National University Computer Vision Lab(CVL)ETH Zurich Department of Electronic EngineeringTsinghua University College of Computer ScienceNankai University 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2023年第66卷第12期

页      面：278-280页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by National Key R&D Program of China (Grant No. 2022ZD0119101) 

摘      要：Large models open up new opportunities for artificial intelligence. In the past few months, there has been a boom in training foundation models on the vast linguistic corpus to produce amazing applications, e.g., Chat GPT, *** natural language processing and multimodal learning communities have been revolutionized. Large models’ capacity for generalization and emergent makes it easy for users to believe that large models can solve anything.