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.
Cite
@article{arxiv.1812.02682,
title = {$\beta$-VAEs can retain label information even at high compression},
author = {Emily Fertig and Aryan Arbabi and Alexander A. Alemi},
journal= {arXiv preprint arXiv:1812.02682},
year = {2018}
}