Posterior Promoted GAN with Distribution Discriminator for Unsupervised Image Synthesis

Sufficient real information in generator is a critical point for the generation ability of GAN. However, GAN and its variants suffer from lack of this point, resulting in brittle training processes. In this paper, we propose a novel variant of GAN, Posterior Promoted GAN (P
²
GAN), which promotes generator with the real information in the posterior distribution produced by discriminator. In our frame-work, different from other variants of GAN, the discriminator maps images to a multivariate Gaussian distribution and extracts real information. The generator employs the real information by AdaIN and a latent code regularizer. Besides, reparameterization trick and pretraining is applied to guarantee a stable training process in practice. The convergence of P
²
GAN is theoretically proved. Experimental results on typical high-dimensional multi-modal datasets demonstrate that P
²
GAN has achieved comparable results with the state-of-the-art variants of GAN on unsupervised image synthesis.