How good is my GAN? - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

How good is my GAN?

Résumé

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.
Fichier principal
Vignette du fichier
ganeval.pdf (1.12 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01850447 , version 1 (27-07-2018)

Identifiants

Citer

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⟩
681 Consultations
5837 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More