Real or Not Real, that is the Question

Abstract

While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. Compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.

ICLR2020 spotlight. 1) train GAN by maximizing kl-divergence. 2) train non-progressive GAN (DCGAN) architecture at 1024*1024 resolution

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks

Cited by in corpus (10)

• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• DeepFaceLab: Integrated, flexible and extensible face-swapping framework
• A Systematic Survey of Regularization and Normalization in GANs
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
• Self-Supervised GANs with Label Augmentation
• Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
• Learning a low dimensional manifold of real cancer tissue with PathologyGAN
• Towards Privacy-preserving Explanations in Medical Image Analysis
• Manifold-preserved GANs
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation