papers AI Learner
The Github is limit! Click to go to the new site.

Isolating Sources of Disentanglement in Variational Autoencoders

2019-04-23
Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud

Abstract

We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our $\beta$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art $\beta$-VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1802.04942

PDF

http://arxiv.org/pdf/1802.04942


Similar Posts

Comments