Generative Multi-Adversarial Networks

Understand

Generative adversarial networks (GANs) are a framework for producing a generative model by way of a two-player minimax game.

• In this paper, we propose the \emph{Generative Multi-Adversarial Network} (GMAN), a framework that extends GANs to multiple discriminators.
• In previous work, the successful training of GANs requires modifying the minimax objective to accelerate training early on.
• In contrast, GMAN can be reliably trained with the original, untampered objective.