Multi-agent Diverse Generative Adversarial Networks

Arnab Ghosh, Viveka Kulharia, Vinay Namboodiri, Philip H.S. Torr, Puneet K. Dokania

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple generators and one discriminator. Second, to enforce that different generators capture diverse high probability modes, the discriminator of MAD-GAN is designed such that along with finding the real and fake samples, it is also required to identify the generator that generated the given fake sample. Intuitively, to succeed in this task, the discriminator must learn to push different generators towards different identifiable modes. We perform extensive experiments on synthetic and real datasets and compare MAD-GAN with different variants of GAN. We show high quality diverse sample generations for challenging tasks such as image-to-image translation and face generation. In addition, we also show that MAD-GAN is able to disentangle different modalities when trained using highly challenging diverse-class dataset (e.g. dataset with images of forests, icebergs, and bedrooms). In the end, we show its efficacy on the unsupervised feature representation task.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PublisherIEEE
Pages8513-8521
Number of pages9
ISBN (Electronic)9781538664209
DOIs
Publication statusPublished - 17 Dec 2018
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, USA United States
Duration: 18 Jun 201822 Jun 2018

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
CountryUSA United States
CitySalt Lake City
Period18/06/1822/06/18

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Ghosh, A., Kulharia, V., Namboodiri, V., Torr, P. H. S., & Dokania, P. K. (2018). Multi-agent Diverse Generative Adversarial Networks. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 8513-8521). [8578986] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE. https://doi.org/10.1109/CVPR.2018.00888