Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability

Abstract The key objective of this study is to propose an effective and accurate deep learning (DL) framework to detect and classify diseases in banana, cherry, and tomato leaves. The performance of multiple pre-trained models is compared against a newly presented model.The experiments used a public...

Full description

Saved in:
Bibliographic Details
Main Authors: Sankar Murugesan, Jayaprakash Chinnadurai, Saravanan Srinivasan, Sandeep Kumar Mathivanan, Radha Raman Chandan, Usha Moorthy
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-14847-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344550683803648
author Sankar Murugesan
Jayaprakash Chinnadurai
Saravanan Srinivasan
Sandeep Kumar Mathivanan
Radha Raman Chandan
Usha Moorthy
author_facet Sankar Murugesan
Jayaprakash Chinnadurai
Saravanan Srinivasan
Sandeep Kumar Mathivanan
Radha Raman Chandan
Usha Moorthy
author_sort Sankar Murugesan
collection DOAJ
description Abstract The key objective of this study is to propose an effective and accurate deep learning (DL) framework to detect and classify diseases in banana, cherry, and tomato leaves. The performance of multiple pre-trained models is compared against a newly presented model.The experiments used a publicly released dataset of healthy and unhealthy leaves from banana, cherry, and tomato plants. This dataset was uniformly split into training, validation, and test sets to obtain consistent and unbiased model evaluations. The data pre-processing also involved pre-processing steps suitable for DL architectures to keep the input the same among all the models.We use several state-of-the-art pre-trained ConvNets models for the baselines, such as EfficientNetV2, ConvNeXt, Swin Transformer, and Vi-Transformer (ViT), to have an outlook on the performance. A new ConvNet-ViT hybrid model combines the ConvNet and ViT layers for local feature extraction and maintaining the global context. The classifier’s performance was reinforced by a 5-fold cross-validation mechanism to avoid overfitting.The proposed Hybrid ConvNet-ViT model outperformed all the compared models evaluated, achieving a testing classification accuracy of 99.29%, which outperforms all the pre-trained models. This finding shows that combining ConvNets’ local feature learning with the capability of global representation of the ViT is effective.The result shows that the Hybrid ConvNet-ViT model is an effective and accurate solution in detecting and classifying plant leaf diseases. Its outstanding performance of the state-of-the-art pre-trained top models positions itself as a solid model for practical agricultural use. Fusing the ConvNet and transformer frameworks jointly is beneficial for improving classification performance in image-based disease detection work.
format Article
id doaj-art-1edb985f06464c8d9fbe749c249af3d0
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1edb985f06464c8d9fbe749c249af3d02025-08-20T03:42:38ZengNature PortfolioScientific Reports2045-23222025-08-0115112210.1038/s41598-025-14847-7Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretabilitySankar Murugesan0Jayaprakash Chinnadurai1Saravanan Srinivasan2Sandeep Kumar Mathivanan3Radha Raman Chandan4Usha Moorthy5Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and TechnologySchool of Computer Science and Engineering, Galgotias UniversityDepartment of Computer Science and Engineering, SRM Institute of Science and TechnologySchool of Computer Science and Engineering, Galgotias UniversityDepartment of Computer Science, School of Management Sciences (SMS)School of Computer Engineering, Manipal Institute of Technology, Bengaluru,, Manipal Academy of Higher EducationAbstract The key objective of this study is to propose an effective and accurate deep learning (DL) framework to detect and classify diseases in banana, cherry, and tomato leaves. The performance of multiple pre-trained models is compared against a newly presented model.The experiments used a publicly released dataset of healthy and unhealthy leaves from banana, cherry, and tomato plants. This dataset was uniformly split into training, validation, and test sets to obtain consistent and unbiased model evaluations. The data pre-processing also involved pre-processing steps suitable for DL architectures to keep the input the same among all the models.We use several state-of-the-art pre-trained ConvNets models for the baselines, such as EfficientNetV2, ConvNeXt, Swin Transformer, and Vi-Transformer (ViT), to have an outlook on the performance. A new ConvNet-ViT hybrid model combines the ConvNet and ViT layers for local feature extraction and maintaining the global context. The classifier’s performance was reinforced by a 5-fold cross-validation mechanism to avoid overfitting.The proposed Hybrid ConvNet-ViT model outperformed all the compared models evaluated, achieving a testing classification accuracy of 99.29%, which outperforms all the pre-trained models. This finding shows that combining ConvNets’ local feature learning with the capability of global representation of the ViT is effective.The result shows that the Hybrid ConvNet-ViT model is an effective and accurate solution in detecting and classifying plant leaf diseases. Its outstanding performance of the state-of-the-art pre-trained top models positions itself as a solid model for practical agricultural use. Fusing the ConvNet and transformer frameworks jointly is beneficial for improving classification performance in image-based disease detection work.https://doi.org/10.1038/s41598-025-14847-7Plant leaf diseaseClassificationConvNetDeep learningVision transformerHybrid ConvNet-ViT
spellingShingle Sankar Murugesan
Jayaprakash Chinnadurai
Saravanan Srinivasan
Sandeep Kumar Mathivanan
Radha Raman Chandan
Usha Moorthy
Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability
Scientific Reports
Plant leaf disease
Classification
ConvNet
Deep learning
Vision transformer
Hybrid ConvNet-ViT
title Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability
title_full Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability
title_fullStr Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability
title_full_unstemmed Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability
title_short Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability
title_sort robust multiclass classification of crop leaf diseases using hybrid deep learning and grad cam interpretability
topic Plant leaf disease
Classification
ConvNet
Deep learning
Vision transformer
Hybrid ConvNet-ViT
url https://doi.org/10.1038/s41598-025-14847-7
work_keys_str_mv AT sankarmurugesan robustmulticlassclassificationofcropleafdiseasesusinghybriddeeplearningandgradcaminterpretability
AT jayaprakashchinnadurai robustmulticlassclassificationofcropleafdiseasesusinghybriddeeplearningandgradcaminterpretability
AT saravanansrinivasan robustmulticlassclassificationofcropleafdiseasesusinghybriddeeplearningandgradcaminterpretability
AT sandeepkumarmathivanan robustmulticlassclassificationofcropleafdiseasesusinghybriddeeplearningandgradcaminterpretability
AT radharamanchandan robustmulticlassclassificationofcropleafdiseasesusinghybriddeeplearningandgradcaminterpretability
AT ushamoorthy robustmulticlassclassificationofcropleafdiseasesusinghybriddeeplearningandgradcaminterpretability