Multi-Agent Diverse Generative Adversarial Networks

  title={Multi-Agent Diverse Generative Adversarial Networks},
  author={Arnab Ghosh and Viveka Kulharia and Vinay P. Namboodiri and Philip H. S. Torr and Puneet Kumar Dokania},
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 MADGAN is designed such that along with finding the real and fake samples, it is also required to identify the… CONTINUE READING
Highly Cited
This paper has 36 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 80 times over the past 90 days. VIEW TWEETS
28 Citations
33 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 28 extracted citations


Publications referenced by this paper.
Showing 1-10 of 33 references

Similar Papers

Loading similar papers…