RMM: Reinforced memory management for class-incremental learning

• Main Authors: LIU, Yaoyao, SUN, Qianru
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/6790; https://ink.library.smu.edu.sg/context/sis_research/article/7793/viewcontent/NeurIPS2021_Submission_Class_Incremental_Learning__2___1_.pdf
• Institution: Singapore Management University

Class-Incremental Learning (CIL) [38] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars used for replaying. However, existing methods use a static an...