loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Sebastian Scherer ; Robin Schön ; Katja Ludwig and Rainer Lienhart

Affiliation: University of Augsburg, Universitatsstraße 1, 86159 Augsburg, Germany

Keyword(s): Self-supervised Learning, Image-to-Image Translation, Semantic Segmentation, Nighttime.

Abstract: This paper deals with the problem of semantic image segmentation of street scenes at night, as the recent advances in semantic image segmentation are mainly related to daytime images. We propose a method to extend the learned domain of daytime images to nighttime images based on an extended version of the CycleGAN framework and its integration into a self-supervised learning framework. The aim of the method is to reduce the cost of human annotation of night images by robustly transferring images from day to night and training the segmentation network to make consistent predictions in both domains, allowing the usage of completely unlabelled images in training. Experiments show that our approach significantly improves the performance on nighttime images while keeping the performance on daytime images stable. Furthermore, our method can be applied to many other problem formulations and is not specifically designed for semantic segmentation.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.208.168.232

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Scherer, S.; Schön, R.; Ludwig, K. and Lienhart, R. (2021). Unsupervised Domain Extension for Nighttime Semantic Segmentation in Urban Scenes. In Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA; ISBN 978-989-758-526-5; ISSN 2184-9277, SciTePress, pages 38-47. DOI: 10.5220/0010551500380047

@conference{delta21,
author={Sebastian Scherer. and Robin Schön. and Katja Ludwig. and Rainer Lienhart.},
title={Unsupervised Domain Extension for Nighttime Semantic Segmentation in Urban Scenes},
booktitle={Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA},
year={2021},
pages={38-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010551500380047},
isbn={978-989-758-526-5},
issn={2184-9277},
}

TY - CONF

JO - Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA
TI - Unsupervised Domain Extension for Nighttime Semantic Segmentation in Urban Scenes
SN - 978-989-758-526-5
IS - 2184-9277
AU - Scherer, S.
AU - Schön, R.
AU - Ludwig, K.
AU - Lienhart, R.
PY - 2021
SP - 38
EP - 47
DO - 10.5220/0010551500380047
PB - SciTePress