Skip to Main content Skip to Navigation
New interface
Conference papers

How good is my GAN?

Konstantin Shmelkov 1 Cordelia Schmid 1 Karteek Alahari 1 
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : Generative adversarial networks (GANs) are one of the most popular methods for generating images today. While impressive results have been validated by visual inspection, a number of quantitative criteria have emerged only recently. We argue here that the existing ones are insufficient and need to be in adequation with the task at hand. In this paper we introduce two measures based on image classification---GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively. We evaluate a number of recent GAN approaches based on these two measures and demonstrate a clear difference in performance. Furthermore, we observe that the increasing difficulty of the dataset, from CIFAR10 over CIFAR100 to ImageNet, shows an inverse correlation with the quality of the GANs, as clearly evident from our measures.
Complete list of metadata

Cited literature [55 references]  Display  Hide  Download
Contributor : Karteek Alahari Connect in order to contact the contributor
Submitted on : Friday, July 27, 2018 - 1:15:33 PM
Last modification on : Wednesday, May 4, 2022 - 12:18:02 PM
Long-term archiving on: : Sunday, October 28, 2018 - 1:24:16 PM


Files produced by the author(s)




Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari. How good is my GAN?. ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.218-234, ⟨10.1007/978-3-030-01216-8_14⟩. ⟨hal-01850447⟩



Record views


Files downloads