Explaining Spatial Relation Detection using Layerwise Relevance Propagation

Gabriel Farrugia, Adrian Muscat

Abstract

In computer vision, learning to detect relationships between objects is an important way to thoroughly understand images. Machine Learning models have been developed in this area. However, in critical scenarios where a simple decision is not enough, reasons to back up each decision are required and reliability comes into play. We investigate the role that geometric, language and depth features play in the task of predicting Spatial Relations by generating feature relevance measures using Layerwise Relevance Propagation. We carry out the evaluation of feature contributions on a per-class basis.

Download


Paper Citation


in Harvard Style

Farrugia G. and Muscat A. (2020). Explaining Spatial Relation Detection using Layerwise Relevance Propagation.In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-402-2, pages 378-385. DOI: 10.5220/0008964003780385


in Bibtex Style

@conference{visapp20,
author={Gabriel Farrugia and Adrian Muscat},
title={Explaining Spatial Relation Detection using Layerwise Relevance Propagation},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2020},
pages={378-385},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008964003780385},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Explaining Spatial Relation Detection using Layerwise Relevance Propagation
SN - 978-989-758-402-2
AU - Farrugia G.
AU - Muscat A.
PY - 2020
SP - 378
EP - 385
DO - 10.5220/0008964003780385