Factors Affecting Accuracy in Image Translation based on Generative Adversarial Network

Fumiya Yamashita, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga

2018

Abstract

With the development of deep learning, image translation has made it possible to output more realistic and highly accurate images. Especially, with the advent of Generative Adversarial Network (GAN), it became possible to perform general purpose learning in various image translation tasks such as “drawings to paintings”, “male to female” and “day to night”. In recent works, several models have been proposed that can do unsupervised learning which does not require an explicit pair of source domain image and target domain image, which is conventionally required for image translation. Two models called “CycleGAN” and “DiscoGAN” have appeared as state-of-the-art models in unsupervised learning-based image translation and succeeded in creating more realistic and highly accurate images. These models share the same network architecture, although there are differences in detailed parameter settings and learning algorithms. (in this paper we will collectively refer to them as “learning techniques”) Both models can do similar translation tasks, but it turned out that there is a large difference in translation accuracy between particular image domains. In this study, we analyzed differences in learning techniques of these models and investigated which learning techniques affect translation accuracy. As a result, it was found that the difference in the size of the feature map, which is the input for the image creation, affects the accuracy.

Paper Citation

in Harvard Style

Yamashita F., Orihara R., Sei Y., Tahara Y. and Ohsuga A. (2018). Factors Affecting Accuracy in Image Translation based on Generative Adversarial Network.In Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-275-2, pages 446-453. DOI: 10.5220/0006591204460453

in Bibtex Style

@conference{icaart18,
author={Fumiya Yamashita and Ryohei Orihara and Yuichi Sei and Yasuyuki Tahara and Akihiko Ohsuga},
title={Factors Affecting Accuracy in Image Translation based on Generative Adversarial Network},
booktitle={Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2018},
pages={446-453},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006591204460453},
isbn={978-989-758-275-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Factors Affecting Accuracy in Image Translation based on Generative Adversarial Network
SN - 978-989-758-275-2
AU - Yamashita F.
AU - Orihara R.
AU - Sei Y.
AU - Tahara Y.
AU - Ohsuga A.
PY - 2018
SP - 446
EP - 453
DO - 10.5220/0006591204460453