We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality.
|Task||Dataset||Model||Metric name||Metric value||Global rank||Compare|
|Image Generation||CIFAR-10||BEGAN||Inception score||5.62||# 10|