Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion

Mango is a crop of vital agronomic and commercial importance, particularly in tropical and subtropical regions. Accurate and timely identification of foliar diseases is essential for maintaining plant health and ensuring sustainable agricultural productivity. This study proposes MangoLeafCMDF-FAMNet...

Full description

Saved in:
Bibliographic Details
Main Author: Ebru Ergün
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1638520/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849247172523982848
author Ebru Ergün
author_facet Ebru Ergün
author_sort Ebru Ergün
collection DOAJ
description Mango is a crop of vital agronomic and commercial importance, particularly in tropical and subtropical regions. Accurate and timely identification of foliar diseases is essential for maintaining plant health and ensuring sustainable agricultural productivity. This study proposes MangoLeafCMDF-FAMNet (cross-modal dynamic fusion with feature attention module (FAM) network), an advanced, hybrid, deep-learning framework designed for the multi-class classification of mango leaf diseases. The model combines two state-of-the-art feature extractors, ConvNeXt and Vision Transformer, to capture local fine-grained textures and global contextual semantics simultaneously. To further improve feature discrimination, a FAM inspired by squeeze-and-excitation networks is integrated into each stage of the backbone. This module adaptively recalibrates channel-wise feature responses to highlight disease-relevant cues while suppressing irrelevant background noise. A novel cross-modal dynamic fusion strategy unifies the complementary strengths of both branches, resulting in highly robust and discriminative feature embeddings. The proposed model was rigorously evaluated using comprehensive metrics such as classification accuracy (CA), recall, precision, Matthews correlation coefficient (MCC) and Cohen’s kappa score on three benchmark datasets: MangoLeafDataset1 (8 classes), MangoLeafDataset2 (5 classes) and MangoLeafDataset3 (8 classes). The experimental results consistently demonstrate the superiority of MangoLeafCMDF-FAMNet over the existing baseline models. It achieves exceptional CA values of 0.9978, 0.9988 and 0.9943 across the respective datasets, alongside strong MCC and Cohen’s kappa scores. These results highlight the effectiveness and generalizability of the proposed framework for automated mango leaf disease diagnosis and contribute to advancing deep learning applications in precision plant pathology.
format Article
id doaj-art-56e01e9bfc124110b2c68c5fcee8592b
institution Kabale University
issn 1664-462X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-56e01e9bfc124110b2c68c5fcee8592b2025-08-20T03:58:18ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-08-011610.3389/fpls.2025.16385201638520Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusionEbru ErgünMango is a crop of vital agronomic and commercial importance, particularly in tropical and subtropical regions. Accurate and timely identification of foliar diseases is essential for maintaining plant health and ensuring sustainable agricultural productivity. This study proposes MangoLeafCMDF-FAMNet (cross-modal dynamic fusion with feature attention module (FAM) network), an advanced, hybrid, deep-learning framework designed for the multi-class classification of mango leaf diseases. The model combines two state-of-the-art feature extractors, ConvNeXt and Vision Transformer, to capture local fine-grained textures and global contextual semantics simultaneously. To further improve feature discrimination, a FAM inspired by squeeze-and-excitation networks is integrated into each stage of the backbone. This module adaptively recalibrates channel-wise feature responses to highlight disease-relevant cues while suppressing irrelevant background noise. A novel cross-modal dynamic fusion strategy unifies the complementary strengths of both branches, resulting in highly robust and discriminative feature embeddings. The proposed model was rigorously evaluated using comprehensive metrics such as classification accuracy (CA), recall, precision, Matthews correlation coefficient (MCC) and Cohen’s kappa score on three benchmark datasets: MangoLeafDataset1 (8 classes), MangoLeafDataset2 (5 classes) and MangoLeafDataset3 (8 classes). The experimental results consistently demonstrate the superiority of MangoLeafCMDF-FAMNet over the existing baseline models. It achieves exceptional CA values of 0.9978, 0.9988 and 0.9943 across the respective datasets, alongside strong MCC and Cohen’s kappa scores. These results highlight the effectiveness and generalizability of the proposed framework for automated mango leaf disease diagnosis and contribute to advancing deep learning applications in precision plant pathology.https://www.frontiersin.org/articles/10.3389/fpls.2025.1638520/fullagricultural imagingConvNeXtcross-modal dynamic fusiondisease classificationmango leafvision transformer
spellingShingle Ebru Ergün
Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion
Frontiers in Plant Science
agricultural imaging
ConvNeXt
cross-modal dynamic fusion
disease classification
mango leaf
vision transformer
title Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion
title_full Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion
title_fullStr Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion
title_full_unstemmed Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion
title_short Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion
title_sort attention enhanced hybrid deep learning model for robust mango leaf disease classification via convnext and vision transformer fusion
topic agricultural imaging
ConvNeXt
cross-modal dynamic fusion
disease classification
mango leaf
vision transformer
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1638520/full
work_keys_str_mv AT ebruergun attentionenhancedhybriddeeplearningmodelforrobustmangoleafdiseaseclassificationviaconvnextandvisiontransformerfusion