On the estimation of the Wasserstein distance in generative models

Thomas Pinetz, Daniel Soukup, Thomas Pock

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung


Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training difficulties and their dependence on arbitrary hyperparameters. One recent improvement in GAN literature is to use the Wasserstein distance as loss function leading to Wasserstein Generative Adversarial Networks (WGANs). Using this as a basis, we show various ways in which the Wasserstein distance is estimated for the task of generative modelling. Additionally, the secrets in training such models are shown and summarized at the end of this work. Where applicable, we extend current works to different algorithms, different cost functions, and different regularization schemes to improve generative models.
TitelGerman Conference on Pattern Recognition
PublikationsstatusVeröffentlicht - 2019


Untersuchen Sie die Forschungsthemen von „On the estimation of the Wasserstein distance in generative models“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren