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

TL;DR

This paper critically evaluates attribution maps used to explain CNN decisions in agriculture and forestry, revealing significant limitations and questioning their reliability for practical use.

Contribution

It provides a comprehensive analysis of attribution maps, highlighting their inconsistencies and misalignments with domain expert insights in agricultural and forestry applications.

Findings

Attribution maps often fail to highlight key features consistently.

AMs frequently misalign with expert-identified important features.

The study questions the practical utility of current attribution methods.

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.