We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation. The framework reveals that many existing UCL approaches overlook cross-task consolidation and try to balance plasticity and stability in a shared embedding space. This results in worse performance due to a lack of within-task data diversity and reduced effectiveness in learning the current task. Our method, Osiris, which explicitly optimizes all three objectives on separate embedding spaces, achieves state-of-the-art performance on all benchmarks, including two novel benchmarks proposed in this paper featuring semantically structured task sequences. Compared to standard benchmarks, these two structured benchmarks more closely resemble visual signals received by humans and animals when navigating real-world environments. Finally, we show some preliminary evidence that continual models can benefit from such realistic learning scenarios.

翻译：我们提出了一个统一的无监督持续学习（UCL）框架，该框架将学习目标分解为针对当前数据和过往数据的不同部分，涵盖了稳定性、可塑性以及跨任务整合。该框架揭示了许多现有UCL方法忽视了跨任务整合，并试图在共享的嵌入空间中平衡可塑性与稳定性。由于缺乏任务内部数据的多样性以及学习当前任务的有效性降低，这导致了更差的性能。我们的方法Osiris在独立的嵌入空间中显式优化所有三个目标，在所有基准测试中实现了最先进的性能，包括本文提出的两个具有语义结构化任务序列的新基准。与标准基准相比，这两个结构化基准更接近于人类和动物在现实世界环境中导航时接收到的视觉信号。最后，我们展示了初步证据，表明持续学习模型能够从这种现实的学习场景中受益。