Mixed batches and symmetric discriminators for GAN training

Thomas Lucas 1 Corentin Tallec 2, 3 Jakob Verbeek 1 Yann Ollivier 4
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
3 TAU - TAckling the Underspeficied
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : Generative adversarial networks (GANs) are powerful generative models based on providing feedback to a generative network via a discriminator network. However, the discriminator usually assesses individual samples. This prevents the dis-criminator from accessing global distributional statistics of generated samples, and often leads to mode dropping: the generator models only part of the target distribution. We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch. The latter score does not depend on the order of samples in a batch. Rather than learning this invariance, we introduce a generic permutation-invariant discriminator architecture. This architecture is provably a universal approximator of all symmetric functions. Experimentally, our approach reduces mode collapse in GANs on two synthetic datasets, and obtains good results on the CIFAR10 and CelebA datasets, both qualitatively and quantitatively.
Type de document :
Communication dans un congrès
ICML - 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01791126
Contributeur : Thomas Lucas <>
Soumis le : jeudi 5 juillet 2018 - 14:41:00
Dernière modification le : vendredi 7 septembre 2018 - 13:56:03

Fichier

mixed_batches_sym_disc_for_gan...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01791126, version 2

Citation

Thomas Lucas, Corentin Tallec, Jakob Verbeek, Yann Ollivier. Mixed batches and symmetric discriminators for GAN training. ICML - 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. 〈hal-01791126v2〉

Partager

Métriques

Consultations de la notice

269

Téléchargements de fichiers

58