Knowledge Commons of Institute of Automation,CAS
Bilateral Memory Consolidation for Continual Learning | |
Xing Nie1,2![]() ![]() ![]() ![]() ![]() | |
2023-06 | |
会议名称 | IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) |
会议日期 | 2023年6月18日–2023年6月22日 |
会议地点 | Montreal, Canada |
摘要 | Humans are proficient at continuously acquiring and integrating new knowledge. By contrast, deep models forget catastrophically, especially when tackling highly long task sequences. Inspired by the way our brains constantly rewrite and consolidate past recollections, we propose a novel Bilateral Memory Consolidation (BiMeCo) framework that focuses on enhancing memory interaction capabilities. Specifically, BiMeCo explicitly decouples model parameters into short-term memory module and long-term memory module, responsible for representation ability of the model and generalization over all learned tasks, respectively. BiMeCo encourages dynamic interactions between two memory modules by knowledge distillation and momentum-based updating for forming generic knowledge to prevent forgetting. The proposed BiMeCo is parameterefficient and can be integrated into existing methods seamlessly. Extensive experiments on challenging benchmarks show that BiMeCo significantly improves the performance ofexisting continual learning methods. For example, combined with the state-of-the-art method CwD [55], BiMeCo brings in significant gains ofaround 2% to 6% while using 2x fewer parameters on CIFAR-100 under ResNet-18. |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 智能进化环境 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57462 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences. 2.School of Artificial Intelligence, University of Chinese Academy of Sciences. 3.Baidu Inc., China. 4.Centre for Artificial Intelligence and Robotics, HK Institute of Science & Innovation, CAS. |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Xing Nie,Shixiong Xu,Xiyan Liu,et al. Bilateral Memory Consolidation for Continual Learning[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Bilateral Memory Con(1031KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论