Hyperprior Induced Unsupervised Disentanglement of Latent Representations

Authors

  • Abdul Fatir Ansari National University of Singapore
  • Harold Soh National University of Singapore

DOI:

https://doi.org/10.1609/aaai.v33i01.33013175

Abstract

We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models. In contrast to current approaches that operate on the evidence lower bound (ELBO), we argue that statistical independence in the latent space of VAEs can be enforced in a principled hierarchical Bayesian manner. To this effect, we augment the standard VAE with an inverse-Wishart (IW) prior on the covariance matrix of the latent code. By tuning the IW parameters, we are able to encourage (or discourage) independence in the learnt latent dimensions. Extensive experimental results on a range of datasets (2DShapes, 3DChairs, 3DFaces and CelebA) show our approach to outperform the β-VAE and is competitive with the state-of-the-art FactorVAE. Our approach achieves significantly better disentanglement and reconstruction on a new dataset (CorrelatedEllipses) which introduces correlations between the factors of variation.

Downloads

Published

2019-07-17

How to Cite

Ansari, A. F., & Soh, H. (2019). Hyperprior Induced Unsupervised Disentanglement of Latent Representations. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3175-3182. https://doi.org/10.1609/aaai.v33i01.33013175

Issue

Section

AAAI Technical Track: Machine Learning