Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
2019-02-09Code Available0· sign in to hype
Yasin Yazici, Bruno Lecouat, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/yasinyazici/Venn_GANOfficialIn papertf★ 0
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.