Enhance the old representations’ adaptability dynamically for exemplar-free continual learning
Authors:
- Kunchi LiKLKunchi Li
- Chaoyue DingCDChaoyue Ding
- Jun WanJWJun Wan
- Shan YuSYShan Yu
- 24 April 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 639
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62476273)
- Beijing Natural Science Foundation (JQ23016)
- Natural Science Foundation of Xiamen Municipality (3502Z202373058)
This publication has 34 references indexed in Scilit:
- Asymmetric patch sampling for contrastive learningPattern Recognition, 2024
- AdaER: An adaptive experience replay approach for continual lifelong learningNeurocomputing, 2023
- GFR: Generic feature representations for class incremental learningNeurocomputing, 2023
- Mutual mentor: Online contrastive distillation network for general continual learningNeurocomputing, 2023
- FOSTER: Feature Boosting and Compression for Class-Incremental Learning2022
- Embracing Change: Continual Learning in Deep Neural NetworksTrends in Cognitive Sciences, 2020
- Continual learning of context-dependent processing in neural networksNature Machine Intelligence, 2019
- Large Scale Incremental Learning2019
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem1989