基于补丁的对比学习与记忆巩固用于在线无监督持续学习
Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning
AI总结：
本文提出在线无监督持续学习范式O-UCL及方法PCMC，通过补丁级对比学习提取特征并聚类构建组合理解，在睡眠期巩固记忆以避免灾难性遗忘，在ImageNet和Places365数据流上表现优异。
摘要：
我们关注一种相对未被探索的学习范式，称为在线无监督持续学习（O-UCL），其中智能体接收非平稳、无标签的数据流，并逐步学习识别越来越多的类别。该范式旨在对现实世界应用进行建模，在这些应用中，遇到新事物是常态，例如探索具有多个未知且随时间变化的实体的地形。与无监督、持续或在线学习的先前工作不同，O-UCL将所有三个领域结合到一个具有挑战性且现实的学习范式中。在这种设置中，智能体被频繁评估，并且必须致力于在数据流的任何时刻保持最佳的可能表示，而不是在预先指定的离线任务结束时。所提出的方法称为基于补丁的对比学习与记忆巩固（PCMC），通过识别和聚类补丁级特征来建立对数据的组合理解。这些补丁级特征的嵌入是通过基于补丁的对比学习训练的编码器提取的。PCMC将新数据纳入其分布，同时避免灾难性遗忘，并在“睡眠”期间巩固记忆样本。我们在从ImageNet和Places365数据集创建的数据流上评估PCMC的性能。此外，我们探索了PCMC算法的各种版本，并将其性能与几种现有方法和简单基线进行了比较。
英文摘要：
We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream and progressively learns to identify an increasing number of classes. This paradigm is designed to model real-world applications where encountering novelty is the norm, such as exploring a terrain with several unknown and time-varying entities. Unlike prior work in unsupervised, continual, or online learning, O-UCL combines all three areas into a single challenging and realistic learning paradigm. In this setting, agents are frequently evaluated and must aim to maintain the best possible representation at any point of the data stream, rather than at the end of pre-specified offline tasks. The proposed approach, called \textbf{P}atch-based \textbf{C}ontrastive learning and \textbf{M}emory \textbf{C}onsolidation (PCMC), builds a compositional understanding of data by identifying and clustering patch-level features. Embeddings for these patch-level features are extracted with an encoder trained via patch-based contrastive learning. PCMC incorporates new data into its distribution while avoiding catastrophic forgetting, and it consolidates memory examples during ``sleep" periods. We evaluate PCMC's performance on streams created from the ImageNet and Places365 datasets. Additionally, we explore various versions of the PCMC algorithm and compare its performance against several existing methods and simple baselines.
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。
