Dropout Induced Noise for Co-Creative GAN Systems

ICCVW 2019 pp. 3137-3140

doi:10.1109/ICCVW.2019.00383 /iccvw/2019/wieluch2019iccvw-dropout/

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.

PDF ICCVW Semantic Scholar

Cite

Text

Wieluch and Schwenker. "Dropout Induced Noise for Co-Creative GAN Systems." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00383

Markdown

[Wieluch and Schwenker. "Dropout Induced Noise for Co-Creative GAN Systems." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/wieluch2019iccvw-dropout/) doi:10.1109/ICCVW.2019.00383

BibTeX

@inproceedings{wieluch2019iccvw-dropout,
  title     = {{Dropout Induced Noise for Co-Creative GAN Systems}},
  author    = {Wieluch, Sabine and Schwenker, Friedhelm},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3137-3140},
  doi       = {10.1109/ICCVW.2019.00383},
  url       = {https://mlanthology.org/iccvw/2019/wieluch2019iccvw-dropout/}
}