Medical image processing can lack images for diagnosis. Generative Adversarial Networks
(GANs) provide a method to train generative models for data augmentation. Synthesized …

Generative adversary networks (GANs) suffer from training pathologies such as instability
and mode collapse. These pathologies mainly arise from a lack of diversity in their …

Labeling images for classification can be expensive. Semi-Supervised Learning (SSL)
Generative Adversarial Network (GAN) methods train good classifiers with a few labeled …

Generative Adversarial Networks (GANs) are difficult to train because of pathologies such as
mode and discriminator collapse. Similar pathologies have been studied and addressed in …

Recurrent neural networks are good at solving prediction problems. However, finding a
network that suits a problem is quite hard because their performance is strongly affected by …

Automatic scene generation is an essential area of research with applications in robotics,
recreation, visual representation, training and simulation, education, and more. This survey …

It can be expensive to label images for classification. Good classifiers or high-quality images
can be trained on unlabeled data with Generative Adversarial Network (GAN) methods. We …

This article presents an approach using parallel/distributed generative adversarial networks
for image data augmentation, applied to generate COVID-19 training samples for …

Modeling, predicting, and forecasting ambient air pollution is an important way to deal with
the degradation of the air quality in our cities because it would be helpful for decision …

Generative adversarial networks (GANs) exhibit training pathologies that can lead to
convergence-related degenerative behaviors, whereas spatially-distributed, coevolutionary …