Abstract
Coffee is a vital agricultural commodity that sustains millions of farmers worldwide, yet its cultivation is increasingly threatened by devastating leaf diseases such as Leaf Rust, Phoma, Cercospora, and Leaf Miner. These diseases reduce photosynthetic efficiency, cause defoliation, and ultimately lower crop yield and quality. Traditional diagnostic methods, including visual inspection and laboratory-based tests such as PCR and ELISA, are often time-consuming, costly, and require expert intervention, making them impractical for large-scale use. To address these challenges, we propose EffResViT-SE FusionNet, a novel hybrid deep learning framework that integrates EfficientNetB3 and ResNet50 enhanced with Squeeze-and-Excitation (SE) blocks for adaptive local feature recalibration, along with a Vision Transformer (ViT) for modeling global contextual dependencies. This fusion design effectively combines CNN-based local feature extraction with transformer-based long-range attention in a unified architecture. The model was trained on a large-scale dataset comprising 58,555 coffee leaf images distributed across five classes: Healthy (18,984), Miner (16,983), Leaf Rust (8336), Cercospora (7681), and Phoma (6571). The dataset was split into 70%, 15%, and 15% testing. Key hyperparameters included the Adam optimizer, a learning rate of 0.001, a batch size of 32, and 80 training epochs, ensuring stable convergence. Experimental results demonstrate the superior capability of the proposed model, achieving an overall classification accuracy of 99%, with precision, recall, and F1-scores all ranging between 98% and 99% across all classes. Comparative analysis confirmed notable improvements over baseline models: ResNet50 (94% accuracy), EfficientNetB3 (95% accuracy), and standalone ViT (97% accuracy). Furthermore, ablation studies validated the critical role of SE blocks and feature fusion with the transformer in achieving optimal performance. These outcomes highlight EffResViT-SE FusionNet as a powerful, precise, and scalable solution for early detection and classification of coffee leaf diseases, supporting timely interventions and promoting sustainable agriculture.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 6
Claim · model-written summary
EffResViT-SE FusionNet reached an overall classification accuracy of 99% on coffee leaf disease images.
CoffeaOrganisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Coffee Leaf Diseases”
e1“achieving an overall classification accuracy of 99%”
Claim · model-written summary
Precision, recall and F1-scores of EffResViT-SE FusionNet ranged between 98% and 99% across all classes.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Coffee Leaf Diseases”
e2“with precision, recall, and F1-scores all ranging between 98% and 99% across all classes”
Claim · model-written summary
EffResViT-SE FusionNet showed notable accuracy improvement over ResNet50 (94% accuracy).
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Coffee Leaf Diseases”
e3“Comparative analysis confirmed notable improvements over baseline models: ResNet50 (94% accuracy), EfficientNetB3 (95% accuracy), and standalone ViT (97% accuracy)”
Claim · model-written summary
EffResViT-SE FusionNet showed notable accuracy improvement over EfficientNetB3 (95% accuracy).
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Coffee Leaf Diseases”
e3“Comparative analysis confirmed notable improvements over baseline models: ResNet50 (94% accuracy), EfficientNetB3 (95% accuracy), and standalone ViT (97% accuracy)”
Claim · model-written summary
EffResViT-SE FusionNet showed notable accuracy improvement over standalone ViT (97% accuracy).
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Coffee Leaf Diseases”
e3“Comparative analysis confirmed notable improvements over baseline models: ResNet50 (94% accuracy), EfficientNetB3 (95% accuracy), and standalone ViT (97% accuracy)”
Claim · model-written summary
Ablation showed that the SE blocks and transformer feature fusion are critical for optimal performance of the coffee leaf classifier.
Not reportedComparatorDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Coffee Leaf Diseases”
e4“the critical role of SE blocks and feature fusion with the transformer in achieving optimal performance”