Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Generative Adversarial Parallelization
Daniel Jiwoong Im, He Ma, Chris Dongjoo Kim, Graham Taylor
Nov 05, 2016 (modified: Dec 13, 2016)ICLR 2017 conference submissionreaders: everyone
Abstract:Generative Adversarial Networks (GAN) have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such as low-resolution images. However, they still prove difficult to train in practice and tend to ignore modes of the data generating distribution. Quantitatively capturing effects such as mode coverage and more generally the quality of the generative model still remain elusive. We propose Generative Adversarial Parallelization (GAP), a framework in which many GANs or their variants are trained simultaneously, exchanging their discriminators. This eliminates the tight coupling between a generator and discriminator, leading to improved convergence and improved coverage of modes. We also propose an improved variant of the recently proposed Generative Adversarial Metric and show how it can score individual GANs or their collections under the GAP model.
TL;DR:Creating Synergy with Multiple Generative Adversarial Networks