CBA：通过持续偏置适配器改进在线持续学习
CBA: Improving Online Continual Learning via Continual Bias Adaptor
AI总结：
针对在线持续学习中的灾难性遗忘与新任务偏置问题，提出可在测试时移除的CBA模块以稳定分类器，并通过理论分析和多基准实验验证其有效性。
摘要：
在线持续学习（CL）旨在从非平稳数据流中学习新知识并巩固先前学到的知识。由于训练设置随时间变化，从不断变化的分布中学习到的模型很容易遗忘先前学到的知识，并偏向于新接收的任务。为解决这一问题，我们提出一个持续偏置适配器（Continual Bias Adaptor，CBA）模块，用于增强分类器网络，使其在训练期间适应灾难性的分布变化，从而使分类器网络能够学习对先前任务的稳定巩固。在测试阶段，CBA可以被移除，不会引入额外的计算成本和内存开销。我们从理论上揭示了所提方法能够有效缓解灾难性分布偏移的原因，并基于四个基于回放的基线和三个公开持续学习基准，通过大量实验实证证明了其有效性。
英文摘要：
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily forgets the previously learned knowledge and biases toward the newly received task. To address this problem, we propose a Continual Bias Adaptor (CBA) module to augment the classifier network to adapt to catastrophic distribution change during training, such that the classifier network is able to learn a stable consolidation of previously learned tasks. In the testing stage, CBA can be removed which introduces no additional computation cost and memory overhead. We theoretically reveal the reason why the proposed method can effectively alleviate catastrophic distribution shifts, and empirically demonstrate its effectiveness through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
