Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based methods have shown promising performance. Unlike previous methods that focus on sample storage or knowledge distillation against catastrophic forgetting, this paper aims to understand why the online learning models fail to generalize well from a new perspective of shortcut learning. We identify shortcut learning as the key limiting factor for online CL, where the learned features may be biased, not generalizable to new tasks, and may have an adverse impact on knowledge distillation. To tackle this issue, we present the online prototype learning (OnPro) framework for online CL. First, we propose online prototype equilibrium to learn representative features against shortcut learning and discriminative features to avoid class confusion, ultimately achieving an equilibrium status that separates all seen classes well while learning new classes. Second, with the feedback of online prototypes, we devise a novel adaptive prototypical feedback mechanism to sense the classes that are easily misclassified and then enhance their boundaries. Extensive experimental results on widely-used benchmark datasets demonstrate the superior performance of OnPro over the state-of-the-art baseline methods. Source code is available at https://github.com/weilllllls/OnPro.

翻译：在线持续学习研究从单次数据流中持续学习的问题，要求模型能适应新数据并缓解灾难性遗忘。近年来，通过存储少量旧数据样本的基于重放的方法展现出良好性能。与以往聚焦于样本存储或知识蒸馏来应对灾难性遗忘的方法不同，本文从捷径学习(shortcut learning)的新视角出发，旨在理解在线学习模型泛化能力不足的深层原因。我们指出捷径学习是在线持续学习的关键限制因素——所学特征可能存在偏差、无法泛化到新任务，并对知识蒸馏产生负面影响。为解决该问题，我们提出了面向在线持续学习的在线原型学习(OnPro)框架。首先，我们提出在线原型均衡策略，通过学习具有代表性的特征来抑制捷径学习，同时获取具备区分性的特征以避免类别混淆，最终在学习新类别时达到能清晰分离所有已见类别的均衡状态。其次，基于在线原型的反馈机制，我们设计了自适应原型反馈(APF)机制来感知易被误分类的类别，并增强其决策边界。在广泛使用的基准数据集上的大量实验结果表明，OnPro方法显著优于当前最优的基线方法。源代码地址：https://github.com/weilllllls/OnPro。