Towards plastic and stable incremental learning: A dual-learner framework with cumulative parameter averaging
- 20 December 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 174
Abstract
No abstract availableFunding Information
- China Meteorological Administration (2024KELL-A001)
- Natural Science Foundation of Beijing Municipality (L231019)
- Shenzhen Science and Technology Innovation Program (KJZD20240903102742055)
- Fundamental Research Funds for the Central Universities (2025JBRC004)
- Fundamental Research Funds for the Central Universities (2022JBQY007)
- Fundamental Research Funds for the Central Universities (2023JBZY037)
- National Natural Science Foundation of China (62276019)
- National Natural Science Foundation of China (62306028)
- National University's Basic Research Foundation of China
This publication has 6 references indexed in Scilit:
- Modality-Specific Interactive Attack for Vision-Language Pre-Training ModelsIEEE Transactions on Information Forensics and Security, 2025
- Variational Data-Free Knowledge Distillation for Continual LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Three types of incremental learningNature Machine Intelligence, 2022
- Continual learning of context-dependent processing in neural networksNature Machine Intelligence, 2019
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017