Reciprocal Adversarial Learning via Characteristic Functions

Abstract

Generative adversarial nets (GANs) have become a preferred tool for tasks involving complicated distributions. To stabilise the training and reduce the mode collapse of GANs, one of their main variants employs the integral probability metric (IPM) as the loss function. This provides extensive IPM-GANs with theoretical support for basically comparing moments in an embedded domain of the \textit{critic}. We generalise this by comparing the distributions rather than their moments via a powerful tool, i.e., the characteristic function (CF), which uniquely and universally comprising all the information about a distribution. For rigour, we first establish the physical meaning of the phase and amplitude in CF, and show that this provides a feasible way of balancing the accuracy and diversity of generation. We then develop an efficient sampling strategy to calculate the CFs. Within this framework, we further prove an equivalence between the embedded and data domains when a reciprocal exists, where we naturally develop the GAN in an auto-encoder structure, in a way of comparing everything in the embedded space (a semantically meaningful manifold). This efficient structure uses only two modules, together with a simple training strategy, to achieve bi-directionally generating clear images, which is referred to as the reciprocal CF GAN (RCF-GAN). Experimental results demonstrate the superior performances of the proposed RCF-GAN in terms of both generation and reconstruction.

This work has been accepted to NeurIPS 2020

References in corpus (23)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Spectral Normalization for Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Which Training Methods for GANs do actually Converge?
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Adversarial Feature Learning
• Adversarially Learned Inference
• Autoencoding beyond pixels using a learned similarity metric
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• The Complex Gradient Operator and the CR-Calculus
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Neural Photo Editing with Introspective Adversarial Networks
• Mode Regularized Generative Adversarial Networks
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• Learning in Implicit Generative Models
• Demystifying MMD GANs
• Do GANs actually learn the distribution? An empirical study
• Fast Two-Sample Testing with Analytic Representations of Probability Measures
• A Convex Duality Framework for GANs
• McGan: Mean and Covariance Feature Matching GAN
• Solving general elliptical mixture models through an approximate Wasserstein manifold