Explainability and Continuous Learning with Capsule Networks

Janis Mohr, Basil Tousside, Marco Schmidt, Jörg Frochte

2021

Abstract

Capsule networks are an emerging technique for image recognition and classification tasks with innovative approaches inspired by the human visual cortex. State of the art is that capsule networks achieve good accuracy for future image recognition tasks and are a promising approach for hierarchical data sets. In this work, it is shown that capsule networks can generate image descriptions representing detected objects in images. This visualisation in combination with reconstructed images delivers strong and easily understandable explainability regarding the decision-making process of capsule networks and leading towards trustworthy AI. Furthermore it is shown that capsule networks can be used for continuous learning utilising already learned basic geometric shapes to learn more complex objects. As shown by our experiments, our approach allows for distinct explainability making it possible to use capsule networks where explainability is required.

Paper Citation

in Harvard Style

Mohr J., Tousside B., Schmidt M. and Frochte J. (2021). Explainability and Continuous Learning with Capsule Networks. In Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2021) - Volume 1: KDIR; ISBN 978-989-758-533-3, SciTePress, pages 264-273. DOI: 10.5220/0010681300003064

in Bibtex Style

@conference{kdir21,
author={Janis Mohr and Basil Tousside and Marco Schmidt and Jörg Frochte},
title={Explainability and Continuous Learning with Capsule Networks},
booktitle={Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2021) - Volume 1: KDIR},
year={2021},
pages={264-273},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010681300003064},
isbn={978-989-758-533-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2021) - Volume 1: KDIR
TI - Explainability and Continuous Learning with Capsule Networks
SN - 978-989-758-533-3
AU - Mohr J.
AU - Tousside B.
AU - Schmidt M.
AU - Frochte J.
PY - 2021
SP - 264
EP - 273
DO - 10.5220/0010681300003064
PB - SciTePress