InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs

Understand

Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution.

• Recent advances have been dominated by Variational AutoEncoder (VAE)-based methods, while training disentangled generative adversarial networks (GANs) remains challenging.
• In this work, we show that the dominant challenges facing disentangled GANs can be mitigated through the use of self-supervision.
• We make two main contributions: first, we design a novel approach for training disentangled GANs with self-supervision.