L3Net: Localized and Layered Reparameterization for Incremental Learning

• Main Authors: LUO, Xuandi, ZHANG, Huaidong, XIE, Yi, ZHANG, Hongrui, XU, Xuemiao, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2025
• Subjects: Class incremental learning; Knowledge distillation; Reparameterization; Artificial Intelligence and Robotics; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/10141; https://ink.library.smu.edu.sg/context/sis_research/article/11141/viewcontent/ssrn_4992816_sv.pdf

Model-based class incremental learning (CIL) methods aim to address the challenge of catastrophic forgetting by retaining certain parameters and expanding the model architecture. However, retaining too many parameters can lead to an overly complex model, increasing inference overhead. Additionally,...