OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
This work addresses the problem of unsupervised disentanglement for researchers in generative models, offering a novel GAN-based approach that is incremental over prior VAE-focused methods.
The paper tackles unsupervised disentanglement learning by proposing OOGAN, a GAN-based framework with one-hot sampling and orthogonal regularization, which achieves improved disentanglement on higher-resolution images compared to previous methods.
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.