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

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

2019-05-26
Bingchen Liu, Yizhe Zhu, Zuohui Fu, Gerard de Melo, Ahmed Elgammal

Abstract

Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel framework called OOGAN. While previous work mostly attempts to tackle disentanglement learning through VAE and seeks to minimize the Total Correlation (TC) objective with various sorts of approximation methods, we show that GANs have a natural advantage in disentangling with a straightforward latent variable sampling method. 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 improved disentanglement learning. Our experiments on several visual datasets confirm the effectiveness and superiority of this approach.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.10836

PDF

http://arxiv.org/pdf/1905.10836


Similar Posts

Comments