ADVANCING PLANT DISEASE DETECTION THROUGH STATE-OF-THE-ART DEEP LEARNING MODELS LEVER-AGING EFFICIENTNETV2, VISION TRANSFORMER, AND ENSEMBLE TECHNIQUES
DOI:
https://doi.org/10.18623/rvd.v23.8156Keywords:
Plant Disease Detection, Deep Learning, EfficientNetV2, Vision Transformer, DenseNet201, ResNet152V2, Agricultural Artificial IntelligenceAbstract
Plant diseases are still posing a challenge to the productivity, quality of crops, and food security, especially in locations where field diagnosis is based on manual visual inspec-tion. This paper assesses deep learning network-based automated classification of plant leaf diseases on public RGB leaf-image datasets, such as the Kaggle New Plant Diseases Dataset (Augmented) and PlantVillage images. They investigated four archi-tectures: EfficientNetV2B0, ResNet152V2, DenseNet201, and one hybrid Vision Trans-former (ViT)-based model. The steps of the experiment involved loading the dataset, exploratory analysis, preprocessing, resizing, normalizing, augmentation, transfer learning, independent model training, and evaluation metrics such as accuracy, preci-sion, recall, F1-score, training curves, testing results, and confusion matrices. The hy-brid ViT-based model was reported to have the best accuracy of 99.5%. On the smaller seven class subset of PlantVillage, EfficientNetV2B0 scored 98.11%. On the 38-class dataset, DenseNet201 improved test accuracy (97.34) and validation classification ac-curacy (around 98). ResNet152V2 scored 97.01 on the 38-class test set. The results demonstrate that CNN and transformer-based models can help to recognize plant diseases accurately whereas hybrid attention-based structures provide a promising path to enhance fine-grained classification. Since the model notebooks had varying class settings and splits, the comparison is seen as a model-structured assessment as opposed to a precisely identical benchmark across all architectures.
References
Aboelenin, S., Elbasheer, F. A., Eltoukhy, M. M., Elhady, W. M., & Hosny, K. M. (2025). A hybrid framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer. Complex & Intelligent Systems, 11(2). https://doi.org/10.1007/s40747-024-01764-x
Aderinwale, D. A., & Şah, M. (2025). Plant disease classification using an ensemble learning model of convolutional neural networks and vision transformers. https://doi.org/10.1109/ichora65333.2025.11017080
Al Sahili, A., Shalash, W., & Tharwat, A. (2023). Transfer learning in agricultural applications: AgriNet for plant disease detection. Agricultural Data Science, 7(2), 77–89.
Albahli, S. (2025). AgriFusionNet: A lightweight deep learning model for multisource plant disease diagnosis. Agriculture, 15(14), Article 1523. https://doi.org/10.3390/agriculture15141523
Albattah, W., Javed, A., Nawaz, M., Masood, M., & Albahli, S. (2022). Artificial intelligence-based drone system for multiclass plant disease detection using an improved efficient convolutional neural network. Frontiers in Plant Science, 13. https://doi.org/10.3389/fpls.2022.808380
Amarnath, A., & Basha, S. M. (2025). Lightweight CNN transformer hybrid for real-time leaf disease detection on mobile devices: A review. International Journal of Engineering Development and Research, 13(3). https://doi.org/10.56975/ijedr.v13i3.301798
Borhani, Y., Khoramdel, J., & Najafi, E. (2022). A deep learning-based approach for automated plant disease classification using vision transformer. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-15163-0
Das, P. K., Sarker Rupa, S., Pumrin, S., Das, U. C., & Hossen, M. K. (2024). Deep learning for plant disease detection and classification: A systematic analysis and review. Current Applied Science and Technology, 24(4), Article e0259016. https://doi.org/10.55003/cast.2024.259016
Guo, M., & Guerra-Manzanares, A. (2026). CROPPER: An explainable lightweight attention-guided ensemble for robust plant disease diagnosis in data-scarce conditions. Applied Soft Computing, 115020. https://doi.org/10.1016/j.asoc.2026.115020
Hamed, B. S., Hussein, M. M., & Mousa, A. M. (2023). Plant disease detection using deep learning. International Journal of Intelligent Systems and Applications, 15(6), 38–50. https://doi.org/10.5815/ijisa.2023.06.04
Hamdi, E. B., & Hidayaturrahman, H. (2024). Ensemble of pre-trained vision transformer models in plant disease classification, an efficient approach. Procedia Computer Science, 245, 565–573. https://doi.org/10.1016/j.procs.2024.10.283
Hemalatha, S., & Jayachandran, J. J. B. (2024). A multitask learning-based vision transformer for plant disease localization and classification. International Journal of Computational Intelligence Systems, 17(1). https://doi.org/10.1007/s44196-024-00597-3
Hukkeri, G. S., Soundarya, B. C., Gururaj, H. L., & Ravi, V. (2024). Classification of various plant leaf disease using pretrained convolutional neural network on ImageNet. The Open Agriculture Journal, 18, Article e18743315305194. https://doi.org/10.2174/0118743315305194240408034912
Jia, S., Wang, G., Li, H., Liu, Y., Shi, L., & Yang, S. (2025). ConvTransNet-S: A CNN-transformer hybrid disease recognition model for complex field environments. Plants, 14(15), Article 2252. https://doi.org/10.3390/plants14152252
Jiang, P., Chen, Y., Liu, B., He, D., & Liang, C. (2019). Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks. IEEE Access, 7, 59069–59080. https://doi.org/10.1109/ACCESS.2019.2914929
Kafi, M. A. A., Banshal, S. K., Moni, R., Aziz, A. L., Aljuaid, M., & Bansal, R. (2026). LeafAI: Interpretable plant disease detection for edge computing. PLOS ONE, 21(1). https://doi.org/10.1371/journal.pone.0335956
Karthikeyan, S., Charan, R., Narayanan, S., & Jani Anbarasi, L. (2025). Enhanced plant disease classification with attention-based convolutional neural network using squeeze and excitation mechanism. Frontiers in Artificial Intelligence, 8, Article 1640549. https://doi.org/10.3389/frai.2025.1640549
Kaur, M., Singh, R., Alirezaee, S., & Hussain, I. (2025). Visual-language transformer-based tomato leaf disease detection for portable greenhouse monitoring device. Plant Methods, 21(1). https://doi.org/10.1186/s13007-025-01456-8
Kerkech, A., & Boulila, W. (2019). Vine disease detection in UAV multispectral images using deep learning. Computers and Electronics in Agriculture, 168, 105–118.
Khaldia, A., & Kalmouna, E. (2024). Automated disease diagnosis in pumpkin plants using advanced CNN models. Computational Biology and Medicine, 57, 45–59.
Krishna, M. S., Machado, P., Otuka, R. I., Yahaya, S. W., Neves dos Santos, F., & Ihianle, I. K. (2025). Plant leaf disease detection using deep learning: A multi dataset approach. J, 8(1), Article 4. https://doi.org/10.3390/j8010004
Li, G., Wang, Y., Zhao, Q., Yuan, P., & Chang, B. (2023). PMVT: A lightweight vision transformer for plant disease identification on mobile devices. Frontiers in Plant Science, 14. https://doi.org/10.3389/fpls.2023.1256773
Li, L.-H., & Tanone, R. (2024). Ensemble learning based on CNN and transformer models for leaf diseases classification. https://doi.org/10.1109/imcom60618.2024.10418393
Li, M., Cheng, S., Cui, J., Li, C., Li, Z., Zhou, C., & Lv, C. (2023). High-performance plant pest and disease detection based on model ensemble with inception module and cluster algorithm. Plants, 12(1), Article 200. https://doi.org/10.3390/plants12010200
Li, W. J., Luo, Y., Jiang, P., Dong, X., Tang, K., Liang, Z., & Shi, Y. (2025). Sustainable crop protection through integrated technologies: UAV-based detection, real-time pesticide mixing, and adaptive spraying. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-19473-x
Masood, A., & Zubair, M. (2020). Early disease diagnosis for rice crop using deep learning. Journal of Computer Science, 15(3), 98–110.
Murugesan, S., Chinnadurai, J., Srinivasan, S., Mathivanan, S. K., Chandan, R. R., & Moorthy, U. (2025). Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-14847-7
Njoroge, T. K. (2025). Multiscale fusion at what cost? Quantifying efficiency-accuracy trade-offs in hybrid models. Journal of Information Systems Engineering & Management, 10, 227–241. https://doi.org/10.52783/jisem.v10i54s.11055
Njoroge, T. K., Kibuku, R., & Mugoye, K. (2025). Comparative and edge-hybrid modeling of EfficientNetV2 and MobileNetV2 for multi-class crop disease classification with statistical validation. Journal of Edge Computing, 4(2), 234–262. https://doi.org/10.55056/jec.905
Pal, R., Bhaumik, A. B., & Maity, B. (2024). Plant disease detection from leaf images using low computational devices. Journal of Machine Learning in Agriculture, 10(1), 83–99.
Paneru, B., Paneru, B., & Shah, K. B. (2021). Rice leaf disease prediction using deep convolutional neural networks. Journal of Precision Agriculture, 23(1), 56–70.
Rahman, K. N., Banik, S. C., Islam, R., & Al Fahim, A. (2025). A real-time monitoring system for accurate plant leaves disease detection using deep learning. Crop Design, 4(1), Article 100092. https://doi.org/10.1016/j.cropd.2024.100092
Rezaei, M., Razzak, M., & Singh, M. (2024). Plant disease recognition using few-shot learning. Journal of Agricultural Informatics, 15(2), 112–125.
Sahu, K., Tiwari, S., Singh, M. K., et al. (2025). Plant disease detection using a hybrid dilated CNN with attention mechanisms and optimized Mask R-CNN segmentation. Scientific Reports, 15, Article 42008. https://doi.org/10.1038/s41598-025-26192-w
Saif, A., & Li, X. (2023). Plant disease detection using deep learning techniques: PLANTSCARE framework. Artificial Intelligence in Agriculture, 6(1), 28–40.
Sennan, S. (2025). A hybrid vision transformer and ResNet18 based model for plant disease detection. Frontiers in Plant Science. https://doi.org/10.3389/fpls.2025.1711700
Shafay, M., Hassan, T., Owais, M., Hussain, I., Khawaja, S. G., Seneviratne, L., & Werghi, N. (2025). Recent advances in plant disease detection: Challenges and opportunities. Plant Methods, 21(1). https://doi.org/10.1186/s13007-025-01450-0
Shahid, M. F., Khanzada, T. J. S., Aslam, M. A., Hussain, S. S., Baowidan, S., & Ashari, R. B. (2024). An ensemble deep learning models approach using image analysis for cotton crop classification in AI-enabled smart agriculture. Plant Methods, 20(1). https://doi.org/10.1186/s13007-024-01228-w
Shrotriya, A., Sharma, A., Bairwa, A. K., & Manoj, R. (2024). Hybrid ensemble learning with CNN and RNN for multimodal cotton plant disease detection. IEEE Access, 12, 198028–198045. https://doi.org/10.1109/access.2024.3515843
Singh, S. N., & Goel, N. (2025). Integrating CNN ensembles and vision transformers for accurate classification of plant leaf diseases. https://doi.org/10.1109/aece67531.2025.11386668
Sujatha, R., Krishnan, S., Chatterjee, J. M., & Gandomi, A. H. (2024). Advancing plant leaf disease detection integrating machine learning and deep learning. Scientific Reports, 15, Article 11552. https://doi.org/10.1038/s41598-024-72197-2
Uzhinskiy, A. (2025). Efficient pipeline for plant disease classification using ConvNeXt. NSR Journal, 32, Article 32. https://doi.org/10.54546/NaturalSciRev.100201
Wang, Y., Gao, X., Liu, J., Pan, X., Luo, X., & Ma, C. (2026). CropHealthyNet: A lightweight hybrid network for efficient crop disease detection. Applied Sciences, 16(3), Article 1329. https://doi.org/10.3390/app16031329
Wu, X., Deng, H., Wang, Q., Lei, L., Gao, Y., & Hao, G. (2023). Meta-learning shows great potential in plant disease recognition under few available samples. The Plant Journal, 114(4), 767–782. https://doi.org/10.1111/tpj.16176
Yang, B., Li, M., Li, F., Wang, Y., Liang, Q., Zhao, R., Li, C., & Wang, J. (2024). A novel plant type, leaf disease and severity identification framework using CNN and transformer with multi-label method. Scientific Reports, 14(1).
Yuliansyah, I., Alashkar, M., & Alsolami, F. (2021). Evaluation of deep learning techniques for plant disease detection. International Journal of Advanced Computer Science and Applications, 12(6), 45–59.
Downloads
Published
How to Cite
Issue
Section
License
I (we) submit this article which is original and unpublished, of my (our) own authorship, to the evaluation of the Veredas do Direito Journal, and agree that the related copyrights will become exclusive property of the Journal, being prohibited any partial or total copy in any other part or other printed or online communication vehicle dissociated from the Veredas do Direito Journal, without the necessary and prior authorization that should be requested in writing to Editor in Chief. I (we) also declare that there is no conflict of interest between the articles theme, the author (s) and enterprises, institutions or individuals.
I (we) recognize that the Veredas do Direito Journal is licensed under a CREATIVE COMMONS LICENSE.
Licença Creative Commons Attribution 3.0
