Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions

Abstract

We propose a GAN design which models multiple distributions effectively and discovers their commonalities and particularities. Each data distribution is modeled with a mixture of $K$ generator distributions. As the generators are partially shared between the modeling of different true data distributions, shared ones captures the commonality of the distributions, while non-shared ones capture unique aspects of them. We show the effectiveness of our method on various datasets (MNIST, Fashion MNIST, CIFAR-10, Omniglot, CelebA) with compelling results.

References in corpus (9)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• cGANs with Projection Discriminator
• The Unusual Effectiveness of Averaging in GAN Training
• Multi-Generator Generative Adversarial Nets
• Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking
• Class-Distinct and Class-Mutual Image Generation with GANs