A parameter-efficient hybrid deep learning architecture that combines DenseNet121 with a lightweight Vision Transformer (ViT) module that shows stable convergence behavior, a good precision-recall balance, and effective training behavior with various dataset sizes is presented.
Abstract
Artificial intelligence (AI) has significantly enhanced image-based analysis across many domains, including agriculture. Deep learning methods have demonstrated strong potential for automated plant disease detection, which is critical to enhancing crop production and precision agriculture. Nevertheless, the diagnosis of plant diseases remains challenging due to unclear backgrounds, high inter-class similarity, and substantial intra-class variability across crop species. To overcome these issues, this paper presents a parameter-efficient hybrid deep learning architecture that combines DenseNet121 with a lightweight Vision Transformer (ViT) module. Instead of using many spatial patches, as in conventional ViT models, the presented framework limits the transformer to a single CNN-derived global token, which is used for lightweight feature refinement at low computational cost. The model is tested on five publicly available agricultural datasets: corn leaf, tomato leaf, BananaLSD, MangoLeafBD, and groundnut leaf. Experimental findings show consistently high performance across all datasets, with accuracies of 97.50%, 99.60%, 98.94%, 99.88%, and 99.66%, respectively. The proposed architecture shows stable convergence behavior, a good precision-recall balance, and effective training behavior with various dataset sizes. Additionally, Grad-CAM visualizations were used to enhance model explainability, highlighting leaf-relevant regions and providing qualitative indications of image regions contributing to predictions.
The results indicate that adding biological structure to model design reduces confusion, helps prevent imbalance effects and increases robustness, providing a more trustworthy and interpretable solution for real-world agricultural disease diagnosis.
A. Luna-Maldonado, N. Hajraoui, Harshinisree Gunasekaran et al.· Frontiers in Artificial Inte...· 0 citations
A deep hybrid Convolutional Neural Network –Transformer architecture is introduced by combining ConvNeXt Large (ConvNeXt-L) and Swin Transformer architecture by combining ConvNeXt Large (ConvNeXt-L) and Swin Transformer (as local feature extractor) and Swin Transformer (as global context encoder) to predict tomato leaf diseases.
Corn Transfer Learning Network (CTL-Net), an end-to-end hybrid deep learning model for corn leaf disease identification, allows accurate and interpretable predictions in a computationally efficient manner, making it an excellent candidate for mobile and resource-limited applications in precision agriculture.
K. P. Kumar, Y. Kuma· Engineering, Technology &...· 0 citations
This study proposes a hybrid technique that integrates attention-weighted exponential pooling (AWEP) with CNN and Vision Transformer (ViT) to enhance feature representation and significantly improve classification performance and highlights that ViT improves embedding separability through t‑distributed stochastic neighbor embedding (t-SNE), thereby reducing overfitting and producing fewer misclassifications in visually similar classes.
Maddassar Jalal, Amandeep Kaur· Applied Fruit Science· 0 citations
A novel hybrid deep learning framework integrating Convolutional Neural Networks, Transformer-based attention mechanisms, and Long Short-Term Memory networks for spatio-temporal cotton leaf disease detection and classification is proposed, suitable for intelligent precision agriculture systems and real-time disease monitoring applications.
Prajakta Sunil Gupta, A. V. Zade· International journal of com...· 0 citations
Potato leaf disease poses a significant threat to global food security, causing substantial crop losses that jeopardise agricultural productivity and farmers’ livelihoods worldwide. Existing automated detection frameworks suffer from several persistent limitations, including over-reliance on controlled benchmark datasets, narrow disease class coverage, exclusive use of spatial feature representations, absence of feature selection, and dependence on single-architecture end-to-end pipelines. To address these limitations, this paper proposes ComPo-Net, a novel lightweight ensemble framework that integrates three efficient CNN architectures—ResNet18, ShuffleNet, and MobileNetV2—for nine-class potato leaf disease detection and classification. Deep features are extracted from three intermediate layers of each network, with the Discrete Wavelet Transform applied for dimensionality reduction and cross-network fusion of the higher-dimensional layer features, capturing spectral–spatial information that purely spatial approaches cannot provide, while the remaining layer features are directly concatenated across networks. One-way Analysis of Variance (ANOVA) feature selection is subsequently applied to retain the most statistically significant features from the combined multi-scale, multi-network representation, and seven machine learning classifiers are systematically evaluated to identify the optimal classification strategy. The framework is assessed on a merged dataset of three publicly available benchmarks spanning both controlled and uncontrolled imaging environments, constituting a nine-class evaluation setting not previously addressed at this scale in the literature. ComPo-Net achieves an accuracy of 96.32%, an F1-score of 93.87%, an MCC of 0.9350, and AUC values exceeding 0.993 across all nine classes with Cubic SVM as the best-performing classifier. When compared against methods evaluated on the seven-class uncontrolled-environment dataset—the closest available task setting to ComPo-Net’s nine-class merged benchmark—ComPo-Net surpasses the best-performing comparable method by a margin of 6.45 percentage points, demonstrating the effectiveness of multi-scale ensemble feature extraction combined with spectral–spatial representation and principled feature selection for robust potato leaf disease detection under diverse real-world conditions.