Wakening past concepts without past data: Class-incremental learning from online placebos

• Main Authors: LIU, Yaoyao, LI, Yingying, SCHIELE, Bernt, SUN, Qianru
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: And algorithm; Data class; Deep dives; Formulation; Incremental learning; Learning architectures; Machine learning architecture; Machine-learning; Markov Decision Processes; Model adaption; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/9207; https://ink.library.smu.edu.sg/context/sis_research/article/10212/viewcontent/Liu_Wakening_Past_Concepts_Without_Past_Data_Class_Incremental_Learning_From_Online_WACV_2024_paper.pdf
• Institution: Singapore Management University

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction inconsistencies between old and new models. Such prediction is m...