Leveraging the Spatial Label Structure for Semantic Image Labeling using Random Forests

Manuel Wöllhaf, Ronny Hänsch, Olaf Hellwich

2018

Abstract

Data used to train models for semantic segmentation have the same spatial structure as the image data, are mostly densely labeled, and thus contain contextual information such as class geometry and cooccurrence. We aim to exploit this information for structured prediction. Multiple structured label spaces, representing different aspects of context information, are introduced and integrated into the Random Forest framework. The main advantage are structural subclasses which carry information about the context of a data point. The output of the applied classification forest is a decomposable posterior probability distribution, which allows substituting the prior by information carried by these subclasses. The experimental evaluation shows results superior to standard Random Forests as well as a related method of structured prediction.

Download


Paper Citation


in Harvard Style

Wöllhaf M., Hänsch R. and Hellwich O. (2018). Leveraging the Spatial Label Structure for Semantic Image Labeling using Random Forests. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 193-200. DOI: 10.5220/0006546801930200


in Bibtex Style

@conference{visapp18,
author={Manuel Wöllhaf and Ronny Hänsch and Olaf Hellwich},
title={Leveraging the Spatial Label Structure for Semantic Image Labeling using Random Forests},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={193-200},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006546801930200},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Leveraging the Spatial Label Structure for Semantic Image Labeling using Random Forests
SN - 978-989-758-290-5
AU - Wöllhaf M.
AU - Hänsch R.
AU - Hellwich O.
PY - 2018
SP - 193
EP - 200
DO - 10.5220/0006546801930200
PB - SciTePress