Explainability of Deep Learning-Based Plant Disease Classifiers Through Automated Concept Identification

TL;DR

This paper demonstrates how Automated Concept-based Explanation (ACE) enhances the interpretability of deep learning models in plant disease classification by automatically identifying key visual features and biases, thereby aiding model improvement and trust.

Contribution

The study applies ACE to plant disease classifiers, revealing critical features and biases, and demonstrating its utility for improving model explainability in agriculture.

Findings

ACE identifies relevant disease features and incidental biases.

ACE helps pinpoint areas for model improvement.

Enhanced transparency in plant disease detection models.

Abstract

While deep learning has significantly advanced automatic plant disease detection through image-based classification, improving model explainability remains crucial for reliable disease detection. In this study, we apply the Automated Concept-based Explanation (ACE) method to plant disease classification using the widely adopted InceptionV3 model and the PlantVillage dataset. ACE automatically identifies the visual concepts found in the image data and provides insights about the critical features influencing the model predictions. This approach reveals both effective disease-related patterns and incidental biases, such as those from background or lighting that can compromise model robustness. Through systematic experiments, ACE helped us to identify relevant features and pinpoint areas for targeted model improvement. Our findings demonstrate the potential of ACE to improve the explainability of plant disease classification based on deep learning, which is essential for producing transparent tools for plant disease management in agriculture.