Hyperprior Induced Unsupervised Disentanglement of Latent Representations
By Abdul Fatir Ansari, Harold Soh. 2018
30 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Yee Whye Teh
- Luc Van Gool
- Alexander Lerchner
- Loic Matthey
- Andrew Zisserman
- Dacheng Tao
- Irina Higgins
- Li Fei-Fei
Citations in the corpus
- Towards a Definition of Disentangled Representations (2018, background): “Most of the recent approaches to disentangled representation learning [39, 15, 47, 13, 51, 7, 28], as well as the majority of the disentanglement metrics [39, 15, 47, 27] assume that this property should be true.”
- Disentangling Disentanglement in Variational Autoencoders (2018, background): “independent factors of variation (Alemi et al., 2017; Ansari and Soh, 2019; Burgess et al., 2018; Chen et al., 2018; 2017; Eastwood and Williams, 2018; Esmaeili et al., 2019; Higgins et al., 2016; Kim and Mnih, 2018; Xu and Durrett, 2018; Zhao et al., 2017), typically evaluating this using purposebu”