L3Net: Localized and Layered Reparameterization for Incremental Learning

• المؤلفون الرئيسيون: LUO, Xuandi, ZHANG, Huaidong, XIE, Yi, ZHANG, Hongrui, XU, Xuemiao, HE, Shengfeng
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2025
• الموضوعات: Class incremental learning; Knowledge distillation; Reparameterization; Artificial Intelligence and Robotics; Theory and Algorithms
• الوصول للمادة أونلاين: 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
• المؤسسة: Singapore Management University

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,...