当前位置:
X-MOL 学术
›
arXiv.cs.NE
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Are Disentangled Representations Helpful for Abstract Visual Reasoning?
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2019-05-29 , DOI: arxiv-1905.12506 Sjoerd van Steenkiste, Francesco Locatello, J\"urgen Schmidhuber, Olivier Bachem
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2019-05-29 , DOI: arxiv-1905.12506 Sjoerd van Steenkiste, Francesco Locatello, J\"urgen Schmidhuber, Olivier Bachem
A disentangled representation encodes information about the salient factors
of variation in the data independently. Although it is often argued that this
representational format is useful in learning to solve many real-world
down-stream tasks, there is little empirical evidence that supports this claim.
In this paper, we conduct a large-scale study that investigates whether
disentangled representations are more suitable for abstract reasoning tasks.
Using two new tasks similar to Raven's Progressive Matrices, we evaluate the
usefulness of the representations learned by 360 state-of-the-art unsupervised
disentanglement models. Based on these representations, we train 3600 abstract
reasoning models and observe that disentangled representations do in fact lead
to better down-stream performance. In particular, they enable quicker learning
using fewer samples.
中文翻译:
Disentangled Representations 对抽象视觉推理有帮助吗?
解开的表示独立地编码关于数据中变化的显着因素的信息。尽管人们经常认为这种表示形式在学习解决许多现实世界的下游任务时很有用,但几乎没有经验证据支持这种说法。在本文中,我们进行了一项大规模研究,调查解开表示是否更适合抽象推理任务。使用类似于 Raven 的渐进矩阵的两个新任务,我们评估了由 360 个最先进的无监督解开模型学习的表示的有用性。基于这些表示,我们训练了 3600 个抽象推理模型,并观察到解开的表示确实会导致更好的下游性能。特别是,
更新日期:2020-01-08
中文翻译:
Disentangled Representations 对抽象视觉推理有帮助吗?
解开的表示独立地编码关于数据中变化的显着因素的信息。尽管人们经常认为这种表示形式在学习解决许多现实世界的下游任务时很有用,但几乎没有经验证据支持这种说法。在本文中,我们进行了一项大规模研究,调查解开表示是否更适合抽象推理任务。使用类似于 Raven 的渐进矩阵的两个新任务,我们评估了由 360 个最先进的无监督解开模型学习的表示的有用性。基于这些表示,我们训练了 3600 个抽象推理模型,并观察到解开的表示确实会导致更好的下游性能。特别是,