Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
This addresses the challenge of multi-distribution learning for researchers in generative modeling, though it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of modeling multiple data distributions to discover their commonalities and particularities, achieving compelling results on datasets like MNIST, Fashion MNIST, CIFAR-10, Omniglot, and CelebA.
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.