Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking

Abstract

Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance called the WGAN based on Wasserstein distance can improve on the KL and JS-divergence based GANs, and alleviate the gradient vanishing, instability, and mode collapse issues that are common in the GAN training. In this work, we aim at improving on the WGAN by first generalizing its discriminator loss to a margin-based one, which leads to a better discriminator, and in turn a better generator, and then carrying out a progressive training paradigm involving multiple GANs to contribute to the maximum margin ranking loss so that the GAN at later stages will improve upon early stages. We call this method Gang of GANs (GoGAN). We have shown theoretically that the proposed GoGAN can reduce the gap between the true data distribution and the generated data distribution by at least half in an optimally trained WGAN. We have also proposed a new way of measuring GAN quality which is based on image completion tasks. We have evaluated our method on four visual datasets: CelebA, LSUN Bedroom, CIFAR-10, and 50K-SSFF, and have seen both visual and quantitative improvement over baseline WGAN.

arXiv comment16 pages. 11 figures

References in corpus (21)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Conditional Image Generation with PixelCNN Decoders
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Pixel Recurrent Neural Networks
• Improved Techniques for Training GANs
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• DRAW: A Recurrent Neural Network For Image Generation
• Energy-based Generative Adversarial Network
• Adversarial Feature Learning
• Adversarially Learned Inference
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Unsupervised Cross-Domain Image Generation
• Neural Photo Editing with Introspective Adversarial Networks
• Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
• Least Squares Generative Adversarial Networks
• Boundary-Seeking Generative Adversarial Networks
• Deep Learning Face Attributes in the Wild
• Stacked Generative Adversarial Networks

Cited by in corpus (11)

• How Generative Adversarial Networks and Their Variants Work: An Overview
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• Stabilizing Generative Adversarial Networks: A Survey
• KBGAN: Adversarial Learning for Knowledge Graph Embeddings
• On the Evaluation of Conditional GANs
• RankGAN: A Maximum Margin Ranking GAN for Generating Faces
• Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
• Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data
• Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
• Domain Partitioning Network