Learning a Video Neural Memory with Bias Mitigation for Video Class-Incremental Learning
Open Access
- 28 October 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5007
Abstract
Video class-incremental learning retains old knowledge while learning new actions under limited replay memory. Temporal compression stores more videos but may lose temporal details and introduce discrepancies between compressed and original videos. We propose Video Neural Memory with Bias Mitigation, combining a Spatio-Temporal Neural Memorizer and Contrastive Bias Correction. The Spatio-Temporal Neural Memorizer preserves temporal and task-related information in compact neural video representations. Contrastive Bias Correction uses class-wise adaptation prompts and contrastive learning to reduce compression-induced feature bias. Experiments on three action recognition benchmarks show higher average incremental accuracy than the compared methods under the same replay-memory budgets, including a gain of 9.18% over the strongest baseline on Something-Something V2 with 18 steps.Keywords
Funding Information
- National Natural Science Foundation of China (62577016)
- Shenzhen Science and Technology Program (CJGJZD20250902091905007)
This publication has 45 references indexed in Scilit:
- Spatial-Temporal Side Adaptation with Difference-based Frame Selector for video class-incremental learningDisplays, 2026
- Video Class-Incremental Learning With Clip Based Transformer2024
- Hypercorrelation Evolution for Video Class-Incremental LearningProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Self-Paced Weight Consolidation for Continual LearningIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Contrastive Similarity Matching for Supervised LearningNeural Computation, 2021
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Searching for Activation FunctionsarXiv, 2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992