Structure by Architecture: Structured Representations without Regularization
arxiv(2020)
摘要
We study the problem of self-supervised structured representation learning
using autoencoders for downstream tasks such as generative modeling. Unlike
most methods which rely on matching an arbitrary, relatively unstructured,
prior distribution for sampling, we propose a sampling technique that relies
solely on the independence of latent variables, thereby avoiding the trade-off
between reconstruction quality and generative performance typically observed in
VAEs. We design a novel autoencoder architecture capable of learning a
structured representation without the need for aggressive regularization. Our
structural decoders learn a hierarchy of latent variables, thereby ordering the
information without any additional regularization or supervision. We
demonstrate how these models learn a representation that improves results in a
variety of downstream tasks including generation, disentanglement, and
extrapolation using several challenging and natural image datasets.
更多查看译文
关键词
Autoencoder,Structure,Generative,Architecture,Disentanglement,Regularization,Hybridization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络