Submitted:
16 November 2026
Posted:
17 November 2026
You are already at the latest version
Abstract
Plant diseases are responsible for enormous losses in crop production every year and as a result of that a contributor to the still ongoing food shortage around the world. Preventing the spread of such diseases in field is a priority for farmers to ensure high and steady yield, but the task of doing so is laborious and time consuming. To make the task faster, easier, and less error prone, researchers have proposed the usage of deep learning models for the detection of diseases in field. CNN have established themselves as a reliable, accurate and lightweight option with widespread application. In this paper we will present how these CNN models are employed in the field of plant leaf disease classification, how they work, how one can train and modify one. Additionally a model based on the MobileNetV3-Large architecture with Squeeze and Excitation attention is shown which outperforms the baseline.
Keywords:
CNN
; plant leaf disease
; classification
; PLDC
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.