ACIL: analytic class-incremental learning with absolute memorization and privacy protection

• المؤلفون الرئيسيون: Zhuang, Huiping, Weng, Zhenyu, Xie, Renchunzi, Toh, Kar-Ann, Lin, Zhiping
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2024
• الموضوعات: Computer and Information Science; Class-incremental learning; Data privacy
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/174481; https://proceedings.neurips.cc/paper_files/paper/2022

Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss due to catastrophic forgetting, or invades data privacy by revisiting used exemplars. Inspired by linear learning fo...