β-VAEs can retain label information even at high compression

12/06/2018

∙

by   Emily Fertig, et al.

∙

0

∙

share

In this paper, we investigate the degree to which the encoding of a β-VAE captures label information across multiple architectures on Binary Static MNIST and Omniglot. Even though they are trained in a completely unsupervised manner, we demonstrate that a β-VAE can retain a large amount of label information, even when asked to learn a highly compressed representation.