Learning Unsupervised Cross-domain Image-to-Image Translation using a Shared Discriminator

Rajiv Kumar, Rishabh Dabral, G. Sivakumar

2021

Abstract

Unsupervised image-to-image translation is used to transform images from a source domain to generate images in a target domain without using source-target image pairs. Promising results have been obtained for this problem in an adversarial setting using two independent GANs and attention mechanisms. We propose a new method that uses a single shared discriminator between the two GANs, which improves the overall efficacy. We assess the qualitative and quantitative results on image transfiguration, a cross-domain translation task, in a setting where the target domain shares similar semantics to the source domain. Our results indicate that even without adding attention mechanisms, our method performs at par with attention-based methods and generates images of comparable quality.

Paper Citation

in Harvard Style

Kumar R., Dabral R. and Sivakumar G. (2021). Learning Unsupervised Cross-domain Image-to-Image Translation using a Shared Discriminator. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 256-264. DOI: 10.5220/0010184102560264

in Bibtex Style

@conference{visapp21,
author={Rajiv Kumar and Rishabh Dabral and G. Sivakumar},
title={Learning Unsupervised Cross-domain Image-to-Image Translation using a Shared Discriminator},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={256-264},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010184102560264},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Learning Unsupervised Cross-domain Image-to-Image Translation using a Shared Discriminator
SN - 978-989-758-488-6
AU - Kumar R.
AU - Dabral R.
AU - Sivakumar G.
PY - 2021
SP - 256
EP - 264
DO - 10.5220/0010184102560264
PB - SciTePress