重新审视下游任务中的解耦：关于其对抽象视觉推理必要性的研究
Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning
AI总结：
本文通过跨数据集、方法和架构的实验，证明维度级解耦对抽象视觉推理并非必要，表征信息量才是更优的性能指标。
摘要：
在表征学习中，解耦表征因其以可分离且紧凑的模式编码数据的生成因素而备受青睐。研究人员一直提倡利用解耦表征来完成下游任务，并有令人鼓舞的实证证据。本文进一步研究了解耦表征在下游应用中的必要性。具体而言，我们表明，在抽象视觉推理这一基础下游任务上，维度级解耦表征并非必要。我们提供了反对解耦必要性的大量实证证据，涵盖多个数据集、表征学习方法和下游网络架构。此外，我们的研究结果表明，表征的信息量比解耦性更能指示下游性能。最后，信息量与解耦性之间的正相关解释了以往工作所声称的解耦表征的有用性。源代码可在 https://github.com/Richard-coder-Nai/disentanglement-lib-necessity.git 获取。
英文摘要：
In representation learning, a disentangled representation is highly desirable as it encodes generative factors of data in a separable and compact pattern. Researchers have advocated leveraging disentangled representations to complete downstream tasks with encouraging empirical evidence. This paper further investigates the necessity of disentangled representation in downstream applications. Specifically, we show that dimension-wise disentangled representations are unnecessary on a fundamental downstream task, abstract visual reasoning. We provide extensive empirical evidence against the necessity of disentanglement, covering multiple datasets, representation learning methods, and downstream network architectures. Furthermore, our findings suggest that the informativeness of representations is a better indicator of downstream performance than disentanglement. Finally, the positive correlation between informativeness and disentanglement explains the claimed usefulness of disentangled representations in previous works. The source code is available at https://github.com/Richard-coder-Nai/disentanglement-lib-necessity.git.
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。
