Deep active sampling with self-supervised learning

作     者：Haochen SHI Hui ZHOU Haochen SHI;Hui ZHOU

作者机构：College of Electronic and Information EngineeringNanjing University of Aeronautics and AstronauticsNanjing 211106China College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 211106China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2023年第17卷第4期

页      面：221-223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）] 

主　　题：tried learning overcome 

摘      要：1 ***,some research efforts[1]have tried to combine selfsupervised learning and active learning to reduce the cost of labeling ***,this method is difficult to effectively improve the model performance because it does not consider the feature representation performance of the examples on the pretext *** order to overcome this shortcoming,we propose a deep active sampling framework with self-supervised representation learning.