不依赖回放的在线持续学习新方法，通过多图块自监督提升性能。
Replay-free Online Continual Learning with Self-Supervised MultiPatches
- 从单个样本生成多个图块，在共享空间中拉近同源图块
- 在多个OCL数据流上超越含回放和其它自监督方法
- 适合隐私敏感场景，可直接接入现有自监督学习框架
在线持续学习（OCL）在非平稳数据流上训练模型，每次仅能获取少量样本，通常依赖回放策略。但在隐私要求严格的场景中，回放常被禁止。为此，我们提出持续多图块（CMP），一种可插入现有OCL自监督学习方法的通用模块，无需使用回放样本。CMP从单个样本生成多个图块，并将其投影至共享特征空间，使同源图块相互靠近，但避免完全坍缩为一点。在多个OCL数据流上，CMP表现优于回放策略及其他基于自监督的方法，挑战了回放作为自监督OCL首选方案的地位。
原文摘要 · Abstract (English)
Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However, usage of replay is sometimes forbidden, especially in applications with strict privacy regulations. Therefore, we propose Continual MultiPatches (CMP), an effective plug-in for existing OCL self-supervised learning strategies that avoids the use of replay samples. CMP generates multiple patches from a single example and projects them into a shared feature space, where patches coming from the same example are pushed together without collapsing into a single point. CMP surpasses replay and other SSL-based strategies on OCL streams, challenging the role of replay as a go-to solution for self-supervised OCL.
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。