PDDD-PreTrain: A Series of Commonly Used Pre-Trained Models Support Image-Based Plant Disease Diagnosis.

Abstract

Plant diseases threaten global food security by reducing crop yield; thus, diagnosing plant diseases is critical to agricultural production. Artificial intelligence technologies gradually replace traditional plant disease diagnosis methods due to their time-consuming, costly, inefficient, and subjective disadvantages. As a mainstream AI method, deep learning has substantially improved plant disease detection and diagnosis for precision agriculture. In the meantime, most of the existing plant disease diagnosis methods usually adopt a pre-trained deep learning model to support diagnosing diseased leaves. However, the commonly used pre-trained models are from the computer vision dataset, not the botany dataset, which barely provides the pre-trained models sufficient domain knowledge about plant disease. Furthermore, this pre-trained way makes the final diagnosis model more difficult to distinguish between different plant diseases and lowers the diagnostic precision. To address this issue, we propose a series of commonly used pre-trained models based on plant disease images to promote the performance of disease diagnosis. In addition, we have experimented with the plant disease pre-trained model on plant disease diagnosis tasks such as plant disease identification, plant disease detection, plant disease segmentation, and other subtasks. The extended experiments prove that the plant disease pre-trained model can achieve higher accuracy than the existing pre-trained model with less training time, thereby supporting the better diagnosis of plant diseases. In addition, our pre-trained models will be open-sourced at https://pd.samlab.cn/ and Zenodo platform https://doi.org/10.5281/zenodo.7856293.

Plant phenotyping relevance

植物病害画像を用いた事前学習モデルを開発し、病害識別・検出・セグメンテーションで評価する研究であり、植物の病害状態を画像から抽出する方法が中心です。

Code and data availability

The authors publicly release their PDDD plant disease dataset, pre-trained model weights, and code via their project website and a Zenodo deposit, as stated in the abstract and Data Availability section.