Mixed Membership Generative Adversarial Networks

Mixed Membership Generative Adversarial Networks

2022 IEEE International Conference on Image Processing (ICIP)

10.1109/ICIP46576.2022.9897640

http://dx.doi.org/10.1109/icip46576.2022.9897640

Yasin Yazici, Bruno Lecouat, Kim Hui Yap, Stefan Winkler, Georgios Piliouras, Vijay Chandrasekhar, Chuan-Sheng Foo

18 October 2022

Yazici, Y., Lecouat, B., Yap, K. H., Winkler, S., Piliouras, G., Chandrasekhar, V., & Foo, C.-S. (2022). Mixed Membership Generative Adversarial Networks. 2022 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip46576.2022.9897640

GANs are designed to learn a single distribution, though multiple distributions can be modeled by treating them separately. However, this naive implementation does not consider overlapping distributions. We propose Mixed Membership Generative Adversarial Networks (MMGAN) analogous to mixed-membership models that model multiple distributions and discover their commonalities and particularities. Each data distribution is modeled as a mixture over a common set of generator distributions, and mixture weights are automatically learned from the data. Mixture weights can give insight into common and unique features of each data distribution. We evaluate our proposed MMGAN and show its effectiveness on MNIST and Fashion-MNIST with various settings.

Publisher Copyright

This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H6b0151

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/18780

2381-8549

Institute for Infocomm Research