Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation

Stephan Brehm, Sebastian Scherer, Rainer Lienhart

2022

Abstract

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation. We propose a semantically consistent image-to-image translation method in combination with a consistency regularisation method for UDA. We overcome previous limitations on transferring synthetic images to real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation model that receives additional feedback from semantic labels on both domains. Our method outperforms state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant domain adaptation benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.

Download


Paper Citation


in Harvard Style

Brehm S., Scherer S. and Lienhart R. (2022). Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 131-141. DOI: 10.5220/0010786000003116


in Bibtex Style

@conference{icaart22,
author={Stephan Brehm and Sebastian Scherer and Rainer Lienhart},
title={Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={131-141},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010786000003116},
isbn={978-989-758-547-0},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation
SN - 978-989-758-547-0
AU - Brehm S.
AU - Scherer S.
AU - Lienhart R.
PY - 2022
SP - 131
EP - 141
DO - 10.5220/0010786000003116