Explainability of Deep Learning-Based Plant Disease Classifiers Through Automated Concept Identification
This work addresses the need for transparent tools in agriculture by enhancing explainability for plant disease detection, but it is incremental as it applies an existing method to a specific domain.
The study tackled the problem of improving explainability in deep learning-based plant disease classifiers by applying the Automated Concept-based Explanation (ACE) method to an InceptionV3 model on the PlantVillage dataset, revealing both disease-related patterns and incidental biases like background or lighting that affect model robustness.
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.