Real-time jute leaf disease classification using an explainable lightweight CNN via a supervised and semi-supervised self-training approach

IntroductionTimely detection of jute leaf diseases is vital for sustaining crop health and farmer livelihoods. Existing deep learning approaches often rely on large, annotated datasets, which are costly and time-consuming to produce.Methods and resultsTo address this challenge, a lightweight convolu...

Full description

Bibliographic Details

Published in:	Frontiers in Plant Science
Main Authors:	Meftahul Jannat, Md Shahab Uddin, Mohammad Asif Hasan, Md Saimun Alam, Avijit Paul, Muhammad E. H. Chowdhury, Julfikar Haider
Format:	Article
Language:	English
Published:	Frontiers Media S.A. 2025-10-01
Subjects:	deep learning semi-supervised self-training lightweight CNN grouped convolution squeeze-and-excite jute leaf disease
Online Access:	https://www.frontiersin.org/articles/10.3389/fpls.2025.1647177/full