Picture for Dr. Friedhelm Schwenker

Dr. Friedhelm Schwenker

Dropout Induced Noise for Co-Creative GAN Systems

Add code
Sep 10, 2019
Sabine Wieluch, Dr. Friedhelm Schwenker
Figure 1 for Dropout Induced Noise for Co-Creative GAN Systems
Figure 2 for Dropout Induced Noise for Co-Creative GAN Systems
Figure 3 for Dropout Induced Noise for Co-Creative GAN Systems
Figure 4 for Dropout Induced Noise for Co-Creative GAN Systems

This paper demonstrates how Dropout can be used in Generative Adversarial Networks to generate multiple different outputs to one input. This method is thought as an alternative to latent space exploration, especially if constraints in the input should be preserved, like in A-to-B translation tasks.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon