We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications.
#6 best model for Conditional Image Generation on CIFAR-10
In this paper, we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical counterexample showing that in the more realistic case of distributions that are not absolutely continuous, unregularized GAN training is not always convergent.
We expand on previous work for image quality assessment to provide two new analyses for assessing the discriminability and diversity of samples from class-conditional image synthesis models.
#4 best model for Conditional Image Generation on CIFAR-10
Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic looking images.