Improved Training of Generative Adversarial Networks Using Representative Features

Abstract

Despite the success of generative adversarial networks (GANs) for image generation, the trade-off between visual quality and image diversity remains a significant issue. This paper achieves both aims simultaneously by improving the stability of training GANs. The key idea of the proposed approach is to implicitly regularize the discriminator using representative features. Focusing on the fact that standard GAN minimizes reverse Kullback-Leibler (KL) divergence, we transfer the representative feature, which is extracted from the data distribution using a pre-trained autoencoder (AE), to the discriminator of standard GANs. Because the AE learns to minimize forward KL divergence, our GAN training with representative features is influenced by both reverse and forward KL divergence. Consequently, the proposed approach is verified to improve visual quality and diversity of state of the art GANs using extensive evaluations.

Accepted at ICML 2018

References in corpus (6)

• Energy-based Generative Adversarial Network
• Towards Principled Methods for Training Generative Adversarial Networks
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Mode Regularized Generative Adversarial Networks
• Better Mixing via Deep Representations
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

Cited by in corpus (4)

• A deep learning framework for quality assessment and restoration in video endoscopy
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• Discriminator Feature-based Inference by Recycling the Discriminator of GANs
• Neural Network based Explicit Mixture Models and Expectation-maximization based Learning