Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Quantitatively Evaluating GANs With Divergences Proposed for Training
Daniel Jiwoong Im, He Ma, Graham W. Taylor, Kristin Branson
Feb 15, 2018 (modified: Feb 27, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in terms of both theory and application.
However, we currently lack quantitative methods for model assessment. Because of this, while many GAN variants being proposed, we have relatively little understanding of their relative abilities. In this paper, we evaluate the performance of various types of GANs using divergence and distance functions typically used only for training. We observe consistency across the various proposed metrics and, interestingly, the test-time metrics do not favour networks that use the same training-time criterion. We also compare the proposed metrics to human perceptual scores.
TL;DR:An empirical evaluation on generative adversarial networks
Keywords:Generative adversarial networks
Enter your feedback below and we'll get back to you as soon as possible.