Mixed batches and symmetric discriminators for GAN training - Archive ouverte HAL Access content directly
Conference Papers Year :

Mixed batches and symmetric discriminators for GAN training

(1) , (2, 3) , (1) , (4)


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.
Fichier principal
Vignette du fichier
mixed_batches_sym_disc_for_gans_with_ack (1).pdf (4.18 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01791126 , version 1 (19-06-2018)
hal-01791126 , version 2 (05-07-2018)


  • HAL Id : hal-01791126 , version 2


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. pp.2844-2853. ⟨hal-01791126v2⟩
775 View
442 Download


Gmail Facebook Twitter LinkedIn More