通过自适应对比重放，减少遗忘并提升模型对新数据的泛化能力。
Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
- 用对比学习思想动态选择难分类样本重放，优化分类边界。
- 在三个数据集上显著提升OOD泛化性能，最高增益达13.41%。
- 适合需要持续学习且关注泛化能力的研究与工业应用。
机器学习模型在学习新类别时常出现灾难性遗忘。尽管基于重放的方法表现良好，但易记忆具体样本，难以泛化到分布外（OOD）数据，导致遗忘率高、泛化差。本文揭示了该问题，并提出自适应对比重放（ACR）方法，通过双优化同时训练编码器和分类器。ACR动态筛选误分类样本存入重放缓冲区，保持类别与任务间的平衡表示。该机制有效协调稳定性与可塑性，在Split CIFAR-100上提升13.41%，Split Mini-ImageNet上提升9.91%，Split Tiny-ImageNet上提升5.98%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。