持续学习：通过自适应对比重放实现更少遗忘、更强OOD泛化
Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
AI总结：
针对基于排练的持续学习方法存在的OOD泛化差、遗忘率高的问题，提出自适应对比重放方法ACR，通过双重优化、自适应填充错分类样本均衡表征，实现稳定性与可塑性平衡，在多个数据集上OOD泛化性能显著提升。
摘要：
机器学习模型在学习新类别时，往往会遭遇对先前所学知识的灾难性遗忘问题。目前已有多种方法被提出以缓解这一问题。然而，保留过往类别样本的基于排练的学习方法通常虽能取得不错的性能，但倾向于记住特定样本，难以应对分布外（Out-of-Distribution, OOD）泛化问题，这往往会导致高遗忘率与较差的泛化能力。出人意料的是，这些方法的OOD泛化能力在很大程度上尚未被探究。本文指出了这一问题，并受对比学习和数据中心原则启发，提出了一种简单却有效的策略来解决该问题。我们提出了自适应对比重放（Adaptive Contrastive Replay, ACR）方法，该方法采用双重优化机制同时训练编码器和分类器。ACR会自适应地将被错误分类的样本填充到重放缓冲区中，同时确保类别与任务的表征均衡。通过这种方式优化决策边界，ACR实现了稳定性与可塑性之间的平衡。我们的方法在OOD泛化方面显著优于先前的方法，在Split CIFAR-100上提升了13.41%，在Split Mini-ImageNet上提升了9.91%，在Split Tiny-ImageNet上提升了5.98%。
英文摘要：
Machine learning models often suffer from catastrophic forgetting of previously learned knowledge when learning new classes. Various methods have been proposed to mitigate this issue. However, rehearsal-based learning, which retains samples from previous classes, typically achieves good performance but tends to memorize specific instances, struggling with Out-of-Distribution (OOD) generalization. This often leads to high forgetting rates and poor generalization. Surprisingly, the OOD generalization capabilities of these methods have been largely unexplored. In this paper, we highlight this issue and propose a simple yet effective strategy inspired by contrastive learning and data-centric principles to address it. We introduce Adaptive Contrastive Replay (ACR), a method that employs dual optimization to simultaneously train both the encoder and the classifier. ACR adaptively populates the replay buffer with misclassified samples while ensuring a balanced representation of classes and tasks. By refining the decision boundary in this way, ACR achieves a balance between stability and plasticity. Our method significantly outperforms previous approaches in terms of OOD generalization, achieving an improvement of 13.41\% on Split CIFAR-100, 9.91\% on Split Mini-ImageNet, and 5.98\% on Split Tiny-ImageNet.
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。
