ACIL: analytic class-incremental learning with absolute memorization and privacy protection
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...
Saved in:
Main Authors: | Zhuang, Huiping, Weng, Zhenyu, Xie, Renchunzi, Toh, Kar-Ann, Lin, Zhiping |
---|---|
其他作者: | School of Electrical and Electronic Engineering |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2024
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/174481 https://proceedings.neurips.cc/paper_files/paper/2022 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
An incremental approach to genetic-algorithms-based classification
由: Guan, S.-U., et al.
出版: (2014)
由: Guan, S.-U., et al.
出版: (2014)
相似書籍
-
Revisiting class-incremental learning with pre-trained models: generalizability and adaptivity are all you need
由: Zhou, Da-Wei, et al.
出版: (2024) -
ENHANCING PRIVACY IN MACHINE LEARNING THROUGH THE MINIMIZATION OF MEMORIZATION
由: ZHENG ESTELLE
出版: (2024) -
Incremental evolution of classifier agents using incremental genetic algorithms
由: ZHU FANGMING
出版: (2010) -
Improving feature generalizability with multitask learning in class incremental learning
由: MA, Dong, et al.
出版: (2022) -
Semi-supervised new slot discovery with incremental clustering
由: WU, Yuxia, et al.
出版: (2022)