arXiv Analytics

Sign in

arXiv:1710.10196 [cs.NE]AbstractReferencesReviewsResources

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen

Published 2017-10-27Version 1

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

Comments: Submitted as a conference paper to ICLR 2018
Categories: cs.NE, cs.LG, stat.ML
Related articles: Most relevant | Search more
arXiv:1812.04948 [cs.NE] (Published 2018-12-12)
A Style-Based Generator Architecture for Generative Adversarial Networks
arXiv:1906.04493 [cs.NE] (Published 2019-06-11)
Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization
arXiv:1912.06180 [cs.NE] (Published 2019-12-12)
COEGAN: Evaluating the Coevolution Effect in Generative Adversarial Networks