OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization

  • Bingchen Liu Rutgers University
  • Yizhe Zhu Rutgers University
  • Zuohui Fu Rutgers University
  • Gerard de Melo Rutgers University
  • Ahmed Elgammal Rutgers University

Abstract

Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN). While previous works mostly attempt to tackle disentanglement learning through VAE and seek to implicitly minimize the Total Correlation (TC) objective with various sorts of approximation methods, we show that GANs have a natural advantage in disentangling with an alternating latent variable (noise) sampling method that is straightforward and robust. Furthermore, we provide a brand-new perspective on designing the structure of the generator and discriminator, demonstrating that a minor structural change and an orthogonal regularization on model weights entails an improved disentanglement. Instead of experimenting on simple toy datasets, we conduct experiments on higher-resolution images and show that OOGAN greatly pushes the boundary of unsupervised disentanglement.

Published
2020-04-03
Section
AAAI Technical Track: Machine Learning