Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
School of Electrical and Electronics Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Institute for Infocomm Research, A*STAR（新加坡资讯通信研究院（A*STAR））；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Engineering Systems and Design, Singapore University of Technology and Design（新加坡科技设计大学工程系统与设计学院）；School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore（南洋理工大学电气与电子工程学院）
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
