A deep learning based approach for automated plant disease classification using vision transformer.

Abstract

Plant disease can diminish a considerable portion of the agricultural products on each farm. The main goal of this work is to provide visual information for the farmers to enable them to take the necessary preventive measures. A lightweight deep learning approach is proposed based on the Vision Transformer (ViT) for real-time automated plant disease classification. In addition to the ViT, the classical convolutional neural network (CNN) methods and the combination of CNN and ViT have been implemented for the plant disease classification. The models have been trained and evaluated on multiple datasets. Based on the comparison between the obtained results, it is concluded that although attention blocks increase the accuracy, they decelerate the prediction. Combining attention blocks with CNN blocks can compensate for the speed.

Plant phenotyping relevance

植物画像から病害状態を分類するVision Transformer等の手法開発・比較が研究の中心であり、植物病害フェノタイピングに該当する。

Code and data availability

The paper uses the public Wheat Rust Classification Dataset (Kaggle) and the authors' analysis code is publicly available on GitHub; both are paper-specific, public, and actionable.