Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry

Lars Nieradzik, Henrike Stephani, Jördis Sieburg-Rockel, Stephanie Helmling, Andrea Olbrich, Janis Keuper

2024

Abstract

In this study, we explore the explainability of neural networks in agriculture and forestry, specifically in fertilizer treatment classification and wood identification. The opaque nature of these models, often considered ’black boxes’, is addressed through an extensive evaluation of state-of-the-art Attribution Maps (AMs), also known as class activation maps (CAMs) or saliency maps. Our comprehensive qualitative and quantitative analysis of these AMs uncovers critical practical limitations. Findings reveal that AMs frequently fail to consistently highlight crucial features and often misalign with the features considered important by domain experts. These discrepancies raise substantial questions about the utility of AMs in understanding the decision-making process of neural networks. Our study provides critical insights into the trustworthiness and practicality of AMs within the agriculture and forestry sectors, thus facilitating a better understanding of neural networks in these application areas.

Paper Citation

in Harvard Style

Nieradzik L., Stephani H., Sieburg-Rockel J., Helmling S., Olbrich A. and Keuper J. (2024). Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 483-492. DOI: 10.5220/0012363400003660

in Bibtex Style

@conference{visapp24,
author={Lars Nieradzik and Henrike Stephani and Jördis Sieburg-Rockel and Stephanie Helmling and Andrea Olbrich and Janis Keuper},
title={Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={483-492},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012363400003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry
SN - 978-989-758-679-8
AU - Nieradzik L.
AU - Stephani H.
AU - Sieburg-Rockel J.
AU - Helmling S.
AU - Olbrich A.
AU - Keuper J.
PY - 2024
SP - 483
EP - 492
DO - 10.5220/0012363400003660
PB - SciTePress