GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint

Abstract

We know SGAN may have a risk of gradient vanishing. A significant improvement is WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent from gradient vanishing. Is there any GAN having no gradient vanishing and no 1-Lipschitz constraint on discriminator? We do find one, called GAN-QP. To construct a new framework of Generative Adversarial Network (GAN) usually includes three steps: 1. choose a probability divergence; 2. convert it into a dual form; 3. play a min-max game. In this articles, we demonstrate that the first step is not necessary. We can analyse the property of divergence and even construct new divergence in dual space directly. As a reward, we obtain a simpler alternative of WGAN: GAN-QP. We demonstrate that GAN-QP have a better performance than WGAN in theory and practice.

arXiv commentsimplify some proofs; add reconstruction

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Training of Wasserstein GANs
• Adversarial Feature Learning
• Adversarially Learned Inference
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Least Squares Generative Adversarial Networks

Cited by in corpus (8)

• A survey on GANs for computer vision: Recent research, analysis and taxonomy
• A Systematic Survey of Regularization and Normalization in GANs
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• Fault Detection in New Wind Turbines with Limited Data by Generative Transfer Learning
• Unsupervised Change Detection in Satellite Images with Generative Adversarial Network
• Artist Style Transfer Via Quadratic Potential
• Self Context and Shape Prior for Sensorless Freehand 3D Ultrasound Reconstruction
• When Relation Networks meet GANs: Relation GANs with Triplet Loss