Dropout Induced Noise for Co-Creative GAN Systems

Sabine Wieluch, Friedhelm Schwenker; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

Abstract


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.

Related Material


[pdf]
[bibtex]
@InProceedings{Wieluch_2019_ICCV,
author = {Wieluch, Sabine and Schwenker, Friedhelm},
title = {Dropout Induced Noise for Co-Creative GAN Systems},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}