Improved Training of Wasserstein GANs

Understand

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability.

• The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge.
• We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior.
• We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input.