Advancing Early Blight Detection in Potato Leaves Through ZeroShot Learning.

Abstract

Potatoes are one of the world's most widely cultivated crops, but their yield is coming under mounting pressure from early blight, a fungal disease caused by Alternaria solani . Early detection and accurate identification are key to effective disease management and yield protection. This paper introduces a novel deep learning framework called ZeroShot CNN, which integrates convolutional neural networks (CNNs) and ZeroShot Learning (ZSL) for the efficient classification of seen and unseen disease classes. The model utilizes convolutional layers for feature extraction and employs semantic embedding techniques to identify previously untrained classes. Implemented on the Kaggle potato disease dataset, ZeroShot CNN achieved 98.50% accuracy for seen categories and 99.91% accuracy for unseen categories, outperforming conventional methods. The hybrid approach demonstrated superior generalization, providing a scalable, real-time solution for detecting agricultural diseases. The success of this solution validates the potential in harnessing deep learning and ZeroShot inference to transform plant pathology and crop protection practices.

Plant phenotyping relevance

ジャガイモ葉の病害状態を画像から分類する深層学習手法が論文の中心であり、未学習病害クラスへの汎化性能も評価しているため、植物フェノタイピング手法として採用する。

Code and data availability

The paper's primary phenotyping input is the Kaggle Potato Disease Dataset (2151 labeled potato leaf images: 1000 healthy, 1151 early blight), explicitly declared publicly available in the Data Availability Statement with an authors' URL matching an allowed URL. No author analysis code or trained model checkpoints are.