用于解耦持续学习的 Infinite dSprites：将记忆编辑与泛化分离
Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
AI总结：
本文提出 Infinite dSprites 基准工具，揭示持续学习方法在长任务序列下性能下降问题，并通过学习类不可知变换来规避灾难性遗忘，实现显式控制记忆与遗忘的开放集分类及单样本泛化。
摘要：
机器学习系统持续学习的能力受到灾难性遗忘的阻碍，即神经网络在学习新任务时覆盖先前获取知识的倾向。现有方法通过正则化、参数隔离或重演来缓解这一问题，但它们通常仅在包含少数任务的基准上进行评估。相比之下，人类能够在动态、开放世界环境中进行长时间跨度的学习，毫不费力地记忆陌生物体，并在各种变换下可靠地识别它们。为了在缩小这一差距上取得进展，我们引入了 Infinite dSprites，这是一个简约的工具，用于创建任意长度且完全控制生成因素的持续分类和解耦基准。我们表明，在足够长的时间跨度内，所有主要类型的持续学习方法在这个简单基准上的性能都会恶化。这一结果突出了持续学习中一个重要且先前被忽视的方面：在有限建模容量和任意长学习跨度下，高效学习需要记忆类特定信息并积累关于通用机制的知识。在对生成因素有直接监督的简单设置中，我们展示了学习类不可知变换如何提供一种规避灾难性遗忘并随时间提高分类准确率的方法。我们的方法为在数百个任务上进行持续学习奠定了基础，能够显式控制记忆与遗忘，并强调开放集分类和单样本泛化。
英文摘要：
The ability of machine learning systems to learn continually is hindered by catastrophic forgetting, the tendency of neural networks to overwrite previously acquired knowledge when learning a new task. Existing methods mitigate this problem through regularization, parameter isolation, or rehearsal, but they are typically evaluated on benchmarks comprising only a handful of tasks. In contrast, humans are able to learn over long time horizons in dynamic, open-world environments, effortlessly memorizing unfamiliar objects and reliably recognizing them under various transformations. To make progress towards closing this gap, we introduce Infinite dSprites, a parsimonious tool for creating continual classification and disentanglement benchmarks of arbitrary length and with full control over generative factors. We show that over a sufficiently long time horizon, the performance of all major types of continual learning methods deteriorates on this simple benchmark. This result highlights an important and previously overlooked aspect of continual learning: given a finite modelling capacity and an arbitrarily long learning horizon, efficient learning requires memorizing class-specific information and accumulating knowledge about general mechanisms. In a simple setting with direct supervision on the generative factors, we show how learning class-agnostic transformations offers a way to circumvent catastrophic forgetting and improve classification accuracy over time. Our approach sets the stage for continual learning over hundreds of tasks with explicit control over memorization and forgetting, emphasizing open-set classification and one-shot generalization.
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。
