Class-incremental exemplar compression for class-incremental learning

• المؤلفون الرئيسيون: LUO, Zilin, LIU, Yaoyao, SCHIELE, Bernt, SUN, Qianru
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2023
• الموضوعات: Databases and Information Systems; Graphics and Human Computer Interfaces
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8055; https://ink.library.smu.edu.sg/context/sis_research/article/9058/viewcontent/Luo_Class_Incremental_Exemplar_Compression_for_Class_Incremental_Learning_CVPR_2023_paper.pdf

Exemplar-based class-incremental learning (CIL) finetunes the model with all samples of new classes but few-shot exemplars of old classes in each incremental phase, where the "few-shot" abides by the limited memory budget. In this paper, we break this "few-shot" limit based on a...