融合自监督与监督嵌入，提升小内存持续学习的样本选择效果
Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers
- 构建图结构融合监督与自监督嵌入进行样本选择
- 在低内存下性能优于现有方法，CIFAR-100和TinyImageNet上显著提升
- 无需增加参数或重放缓存，可直接部署于现有框架
灾难性遗忘仍是持续学习（CL）的核心挑战。在严重内存限制下的基于重放的持续学习中，性能高度依赖于重放缓冲区的样本选择策略。现有方法通常使用监督学习得到的嵌入构建记忆缓冲区，但忽略了无类别标注的自监督表示所蕴含的丰富语义信息。本文提出一种新方法——多嵌入重放选择（MERS），用基于图的机制整合监督与自监督嵌入，替代传统选择模块。实验证明，MERS在多种持续学习算法中均优于当前最优选择策略，尤其在低内存条件下表现突出。在CIFAR-100和TinyImageNet上，其性能超越单嵌入基线，且不增加模型参数或重放数据量，是一种实用、可即插即用的增强方案。
原文摘要 · Abstract (English)
Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most existing approaches construct memory buffers using embeddings learned under supervised objectives. However, class-agnostic, self-supervised representations often encode rich, class-relevant semantics that are overlooked. We propose a new method, Multiple Embedding Replay Selection, MERS, which replaces the buffer selection module with a graph-based approach that integrates both supervised and self-supervised embeddings. Empirical results show consistent improvements over SOTA selection strategies across a range of continual learning algorithms, with particularly strong gains in low-memory regimes. On CIFAR-100 and TinyImageNet, MERS outperforms single-embedding baselines without adding model parameters or increasing replay volume, making it a practical, drop-in enhancement for replay-based continual learning.
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。