PCR：用于在线类增量持续学习的基于代理的对比重放
PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning
AI总结：
针对在线类增量持续学习中的灾难性遗忘问题，提出基于代理的对比重放方法（PCR），通过用代理替换对比样本解决类别不平衡并加速收敛，在三个基准数据集上优于现有方法。
摘要：
在线类增量持续学习是持续学习的一项特定任务。它旨在从数据流中持续学习新类别，且数据流的样本仅可见一次，这会导致灾难性遗忘问题，即遗忘旧类别的历史知识。现有的基于重放的方法通过以基于代理或基于对比的重放方式保存和重放部分旧数据，有效地缓解了这一问题。尽管这两种重放方式均有效，但前者由于类别不平衡问题会倾向于新类别，而后者由于样本数量有限，表现出不稳定性且难以收敛。在本文中，我们对这两种重放方式进行了全面分析，并发现它们可以互补。受此发现启发，我们提出了一种名为基于代理的对比重放（PCR）的新型基于重放的方法。其关键操作是在基于对比的方式中，用相应的代理替换锚点的对比样本。它通过有效解决不平衡问题来缓解灾难性遗忘现象，同时保持模型更快的收敛速度。我们在三个真实世界的基准数据集上进行了大量实验，实证结果一致地证明了PCR相对于各种最先进方法的优越性。
英文摘要：
Online class-incremental continual learning is a specific task of continual learning. It aims to continuously learn new classes from data stream and the samples of data stream are seen only once, which suffers from the catastrophic forgetting issue, i.e., forgetting historical knowledge of old classes. Existing replay-based methods effectively alleviate this issue by saving and replaying part of old data in a proxy-based or contrastive-based replay manner. Although these two replay manners are effective, the former would incline to new classes due to class imbalance issues, and the latter is unstable and hard to converge because of the limited number of samples. In this paper, we conduct a comprehensive analysis of these two replay manners and find that they can be complementary. Inspired by this finding, we propose a novel replay-based method called proxy-based contrastive replay (PCR). The key operation is to replace the contrastive samples of anchors with corresponding proxies in the contrastive-based way. It alleviates the phenomenon of catastrophic forgetting by effectively addressing the imbalance issue, as well as keeps a faster convergence of the model. We conduct extensive experiments on three real-world benchmark datasets, and empirical results consistently demonstrate the superiority of PCR over various state-of-the-art methods.
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。
