Concept explainability for plant diseases classification

TL;DR

This paper introduces a novel concept-based explainability method for plant disease classification using deep learning, enhancing transparency and interpretability of models by focusing on human-understandable concepts.

Contribution

It is the first to apply Testing with Concept Activation Vectors (TCAV) in plant disease classification, demonstrating its potential to improve model interpretability.

Findings

Concept-based explanations improve understanding of model decisions

Color, texture, and disease concepts are key factors in classification

Method enhances trust and transparency in automated plant disease detection

Abstract

Plant diseases remain a considerable threat to food security and agricultural sustainability. Rapid and early identification of these diseases has become a significant concern motivating several studies to rely on the increasing global digitalization and the recent advances in computer vision based on deep learning. In fact, plant disease classification based on deep convolutional neural networks has shown impressive performance. However, these methods have yet to be adopted globally due to concerns regarding their robustness, transparency, and the lack of explainability compared with their human experts counterparts. Methods such as saliency-based approaches associating the network output to perturbations of the input pixels have been proposed to give insights into these algorithms. Still, they are not easily comprehensible and not intuitive for human users and are threatened by bias. In this work, we deploy a method called Testing with Concept Activation Vectors (TCAV) that shifts the focus from pixels to user-defined concepts. To the best of our knowledge, our paper is the first to employ this method in the field of plant disease classification. Important concepts such as color, texture and disease related concepts were analyzed. The results suggest that concept-based explanation methods can significantly benefit automated plant disease identification.