Are conditional GANs explicitly conditional?

by   Houssem-eddine Boulahbal, et al.

This paper proposes two important contributions for conditional Generative Adversarial Networks (cGANs) to improve the wide variety of applications that exploit this architecture. The first main contribution is an analysis of cGANs to show that they are not explicitly conditional. In particular, it will be shown that the discriminator and subsequently the cGAN does not automatically learn the conditionality between inputs. The second contribution is a new method, called acontrario, that explicitly models conditionality for both parts of the adversarial architecture via a novel acontrario loss that involves training the discriminator to learn unconditional (adverse) examples. This leads to a novel type of data augmentation approach for GANs (acontrario learning) which allows to restrict the search space of the generator to conditional outputs using adverse examples. Extensive experimentation is carried out to evaluate the conditionality of the discriminator by proposing a probability distribution analysis. Comparisons with the cGAN architecture for different applications show significant improvements in performance on well known datasets including, semantic image synthesis, image segmentation and monocular depth prediction using different metrics including Fréchet Inception Distance(FID), mean Intersection over Union (mIoU), Root Mean Square Error log (RMSE log) and Number of statistically-Different Bins (NDB)


page 1

page 2

page 7

page 11

page 13

page 14

page 15

page 16


Redes Generativas Adversarias (GAN) Fundamentos Teóricos y Aplicaciones

Generative adversarial networks (GANs) are a method based on the trainin...

Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks

In this study, we employ Generative Adversarial Networks as an oversampl...

CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation

This work proposes the continuous conditional generative adversarial net...

MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network

Conditional Generative Adversarial Networks (cGANs) have been used in ma...

Robustness of Conditional GANs to Noisy Labels

We study the problem of learning conditional generators from noisy label...

HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN

In this paper, we present a novel network for high resolution video gene...

Robust conditional GANs under missing or uncertain labels

Matching the performance of conditional Generative Adversarial Networks ...

Please sign up or login with your details

Forgot password? Click here to reset