Generated Tiny-ImageNet samples of SWGAN-GP.

Generated Tiny-ImageNet samples of SWGAN-GP.

Source publication
Preprint
Full-text available
Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models. However, in practice it does not always outperform other variants of GANs. This is mostly due to the imperfect implementation of the Lipschitz condition required by the KR duality. Extensive work h...