Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Introducing Adversarial Dropout in Generative Multi-Adversarial Networks
Gonçalo Mordido, Haojin Yang, Christoph Meinel
Feb 11, 2018 (modified: Feb 11, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:We propose to extend the original generative adversarial networks (GANs) frame- work to multiple discriminators and omit, or dropout, the feedback of each dis- criminator with same probability at the end of each batch. Our approach forces the generator to not rely on a given discriminator to learn how to produce realistic looking samples, but, instead, on a dynamic ensemble of adversaries. This pro- motes variety of the generated samples, leading to a richer generator less prone to mode collapsing. We show preliminary results on MNIST and Fashion-MNIST that sustain our claims.
TL;DR:We propose to reduce mode collapse in GANs by training the generator against a dynamic ensemble of adversaries.