Multi-Generator Generative Adversarial Nets

Abstract

We propose a new approach to train the Generative Adversarial Nets (GANs) with a mixture of generators to overcome the mode collapsing problem. The main intuition is to employ multiple generators, instead of using a single one as in the original GAN. The idea is simple, yet proven to be extremely effective at covering diverse data modes, easily overcoming the mode collapse and delivering state-of-the-art results. A minimax formulation is able to establish among a classifier, a discriminator, and a set of generators in a similar spirit with GAN. Generators create samples that are intended to come from the same distribution as the training data, whilst the discriminator determines whether samples are true data or generated by generators, and the classifier specifies which generator a sample comes from. The distinguishing feature is that internal samples are created from multiple generators, and then one of them will be randomly selected as final output similar to the mechanism of a probabilistic mixture model. We term our method Mixture GAN (MGAN). We develop theoretical analysis to prove that, at the equilibrium, the Jensen-Shannon divergence (JSD) between the mixture of generators' distributions and the empirical data distribution is minimal, whilst the JSD among generators' distributions is maximal, hence effectively avoiding the mode collapse. By utilizing parameter sharing, our proposed model adds minimal computational cost to the standard GAN, and thus can also efficiently scale to large-scale datasets. We conduct extensive experiments on synthetic 2D data and natural image databases (CIFAR-10, STL-10 and ImageNet) to demonstrate the superior performance of our MGAN in achieving state-of-the-art Inception scores over latest baselines, generating diverse and appealing recognizable objects at different resolutions, and specializing in capturing different types of objects by generators.

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Improved Techniques for Training GANs
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Energy-based Generative Adversarial Network
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Adversarially Learned Inference
• Self-Normalizing Neural Networks
• A note on the evaluation of generative models
• How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
• Dual Discriminator Generative Adversarial Nets
• MAGAN: Margin Adaptation for Generative Adversarial Networks
• Ensembles of Generative Adversarial Networks

Cited by in corpus (13)

• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• Dual Discriminator Generative Adversarial Nets
• Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
• Audio inpainting with generative adversarial network
• Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets
• Competitive Training of Mixtures of Independent Deep Generative Models
• Is Discriminator a Good Feature Extractor?
• Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
• A study of semi-supervised speaker diarization system using gan mixture model
• Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
• ChainGAN: A sequential approach to GANs
• Virtual Conditional Generative Adversarial Networks