Progressive Resolution Training with Attention-Enhanced Ensemble Learning for Automated Recognition of Sugarcane Leaf Diseases
DOI:
https://doi.org/10.24237/djes.2026.19202Keywords:
Deep Learning, Sugarcane Disease, Multistage Training, Attention Mechanisms, Test-Time AugmentationAbstract
Sugarcane (Saccharum officinarum) is one of the most economically important crops in the world. However, outbreaks of leaf diseases cause extensive annual yield losses and threaten sugarcane agricultural productivity. Therefore, early and accurate disease detection is vital for effective crop management, yield protection, and food security. This study presents a deep ensemble learning framework, termed CBAM-SugarcaneNet, for the automated recognition of sugarcane leaf diseases under field conditions. The proposed framework integrates progressive multi-resolution training, a Convolutional Block Attention Module (CBAM), focal loss, Sharpness-Aware Minimization (SAM), ensemble learning, and test-time augmentation to address major challenges such as class imbalance, inter-class visual similarity, background variation, and limited training data. A three-stage progressive training strategy was employed using ConvNeXt-Large and EfficientNet-B5/B7 architectures enhanced with CBAM attention modules to improve the accuracy of disease-relevant feature extraction. Focal loss was used to emphasize minority and difficult-to-classify disease classes, whereas SAM improved model generalization by encouraging convergence toward flatter minima. Experiments were conducted on an 11-class sugarcane leaf disease dataset comprising 6,748 images. The proposed framework achieved 97.2% accuracy for single-model deployment, 97.6% for the ensemble configuration, and 98.1% with test-time augmentation, with a mean 5-fold cross-validation accuracy of 98.05% ± 0.14%. Grad-CAM visualizations further confirmed that the model focused on disease-affected leaf regions. The developed framework offers a robust and deployable solution for precision-agriculture-based disease diagnosis in sugarcane.
Downloads
References
[1] F. and A. O. of the U. Nations, “FAOSTAT statistical database,” 2023.
[2] J. Goldemberg, “The Brazilian biofuels industry,” Biotechnol. Biofuels, vol. 1, no. 1, p. 6, 2008, doi: 10.1186/1754-6834-1-6.
[3] G. Kumar and V. Bhatnagar, "Enhancing Sugarcane Leaf Disease Detection with VGG-19 and Feature Selection," 2025 IEEE 6th Global Conference for Advancement in Technology (GCAT), Bangalore, India, 2025, pp. 1-6, doi: 10.1109/GCAT66372.2025.11368571.
[4] G. Singh and K. K. Yogi, “Deep Learning-Based Detection of Early Blight in Potato Leaves Using CNN Architectures,” Potato Res., vol. 68, no. 4, pp. 4139–4161, 2025, doi: 10.1007/s11540-025-09921-6.
[5] M. H. Lye, M. F. A. Fauzi, and L. K. Ming, “Maize Leaf Disease Identification with Large and Lightweight Convolutional Neural Models,” International Journal on Informatics Visualization, vol. 9, no. 2, pp. 592–598, 2025, doi: 10.62527/joiv.9.2.3559.
[6] K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine Learning in Agriculture: A Review,” 2018. doi: 10.3390/s18082674.
[7] I. S. Rajput, S. Tyagi, A. Gupta, and V. Jain, “Advances in Medical Imaging: Using Convolutional Neural Networks for White Blood Cell Identification,” International Journal of Image, Graphics and Signal Processing (IJIGSP), vol. 16, no. 1, pp. 108–125, 2024. doi: 10.5815/ijigsp.2024.01.08
[8] A. Al-Saegh, S. A. Dawwd, and J. M. Abdul-Jabbar, “Towards Efficient Motor Imagery EEG-based BCI Systems using DCNN,” in 2024 Arab ICT Conference (AICTC), IEEE, 2024, pp. 59–66.
[9] D. Weimer, B. Scholz-Reiter, and M. Shpitalni, “Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection,” CIRP Annals, vol. 65, no. 1, pp. 417–420, 2016, doi: https://doi.org/10.1016/j.cirp.2016.04.072.
[10] A. Srivastava, B. Singh Rawat, G. Kumar, V. Bhatnagar and N. Garg, "Cotton Leaf Disease Prediction Using VGG16 and RESNET50," 2024 Parul International Conference on Engineering and Technology (PICET), Vadodara, India, 2024, pp. 1-6, doi: 10.1109/PICET60765.2024.10716173.
[11] S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional Block Attention Module BT - Computer Vision – ECCV 2018,” V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Eds., Cham: Springer International Publishing, 2018, pp. 3–19.
[12] S. Woo et al., “ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 16133–16142. doi: 10.1109/CVPR52729.2023.01548.
[13] N. M. Basheer and A. Al-Saegh, “Segmentation of Medical MRI Images Using Nested U-Net with Attention Mechanism and Fuzzy Pooling.,” Al-Rafadain Engineering Journal, vol. 30, no. 2, 2025.
[14] V. Umamaheswari and S. Kumaravel, “Machine learning for sugarcane disease classification and prediction: A comprehensive survey,” in AIP Conference Proceedings, AIP Publishing LLC, 2024, p. 20279.
[15] A. T. Khan, S. M. Jensen, A. R. Khan, and S. Li, “Plant disease detection model for edge computing devices,” Front. Plant Sci., vol. 14, p. 1308528, 2023.
[16] X. Yang, Z. Peng, and X. Xie, “CaneFocus-Net: A sugarcane leaf disease detection model based on adaptive receptive field and multi-scale fusion,” Sensors, vol. 25, no. 21, p. 6628, 2025, doi: 10.3390/s25216628.
[17] J. G. A. Barbedo, “Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification,” Comput. Electron. Agric., vol. 153, pp. 46–53, 2018, doi:10.1016/j.compag.2018.08.013.
[18] O. Attallah, “Tomato leaf disease classification via compact convolutional neural networks with transfer learning and feature selection,” Horticulturae, vol. 9, no. 2, p. 149, 2023.
[19] K. M. S. Nomani, M. Nuruzzaman, A. Nadia, and M. M. Billal, “Sugarcane Leaf Disease Detection: A Comparative Analysis Using Deep Learning,” in Proceedings of the 3rd International Conference on Computing Advancements, 2024, pp. 139–144.
[20] S. Phadikar and J. Sil, “Rice disease identification using pattern recognition techniques,” in 2008 11th International Conference on Computer and Information Technology, 2008, pp. 420–423. doi: 10.1109/ICCITECHN.2008.4803079.
[21] A. Camargo and J. S. Smith, “An image-processing based algorithm to automatically identify plant disease visual symptoms,” Biosyst. Eng., vol. 102, no. 1, pp. 9–21, 2009.
[22] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Front. Plant Sci., vol. 7, p. 1419, 2016.
[23] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput. Electron. Agric., vol. 145, pp. 311–318, 2018.
[24] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,” Comput. Intell. Neurosci., vol. 2016, p. 3289801, 2016, doi: 10.1155/2016/3289801.
[25] S. B. Jadhav, V. R. Udupi, and S. B. Patil, “Identification of plant diseases using convolutional neural networks,” International Journal of Information Technology, vol. 13, no. 6, pp. 2461–2470, 2021.
[26] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Comput. Electron. Agric., vol. 161, pp. 272–279, 2019, doi: https://doi.org/10.1016/j.compag.2018.03.032.
[27] G. Kumar, G. Singh, V. Bhatnagar, S. Rawat, and A. Bhardwaj, “Feature Selection for Cotton Leaf Disease Using Deep Learning,” in 2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024, 2024. doi: 10.1109/IICCCS61609.2024.10763840.
[28] G. Kumar and V. Bhatnagar, "Key Feature based Classification of Sugarcane Leaf Disease using CNN and SHAP," 2025 Global Conference on Information Technology and Communication Networks (GITCON), Belagavi, India, 2025, pp. 1-8, doi: 10.1109/GITCON65266.2025.11379773.
[29] J. Kainat, S. Sajid Ullah, F. S. Alharithi, R. Alroobaea, S. Hussain, and S. Nazir, “Blended Features Classification of Leaf-Based Cucumber Disease Using Image Processing Techniques,” Complexity, vol. 2021, 2021, doi: 10.1155/2021/9736179.
[30] A. Dash, P. K. Sethy, and S. K. Behera, “Maize disease identification based on optimized support vector machine using deep feature of DenseNet201,” J. Agric. Food Res., vol. 14, p. 100824, 2023, doi: https://doi.org/10.1016/j.jafr.2023.100824.
[31] P. Tm, A. Pranathi, K. SaiAshritha, N. B. Chittaragi, and S. G. Koolagudi, “Tomato Leaf Disease Detection Using Convolutional Neural Networks,” in 2018 Eleventh International Conference on Contemporary Computing (IC3), 2018, pp. 1–5. doi: 10.1109/IC3.2018.8530532.
[32] M. Tariq, X. Cai, I. Ullah, M. A. Shah, M. S. Soomro, and C. A. Ali, “Automated Detection and Classification of Tomato Leaf Diseases Using Efficient NetB0 and Deep Learning Techniques,” International Journal of Innovations in Science & Technology, vol. 7, no. 3, pp. 2212–2224, 2025.
[33] N. Ullah, B. Ahmad, A. Khan, I. Khan, I. M. Khan, and S. Khan, “Attention-Guided Wheat Disease Recognition Network through Multi-Scale Feature Optimization,” ICCK Transactions on Sensing, Communication, and Control, vol. 2, no. 1, pp. 11–24, 2025, doi: 10.62762/TSCC.2025.435806.
[34] M. H. Tunio et al., “RiceNet: a robust ensemble attention mechanism for automated rice plant disease classification,” Multimed. Tools Appl., vol. 84, no. 39, pp. 48145–48173, 2025, doi: 10.1007/s11042-025-20979-9.
[35] N. V., Y. G., N. N. B., M. R., and P. P., “Empirical Analysis of Squeeze and Excitation-Based Densely Connected CNN for Chili Leaf Disease Identification,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 4, pp. 1681–1692, 2024, doi: 10.1109/TAI.2024.3364126.
[36] A. Narmilan, F. Gonzalez, A. S. Salgadoe, and K. Powell, “Detection of White Leaf Disease in Sugarcane Using Machine Learning Techniques over UAV Multispectral Images,” 2022. doi: 10.3390/drones6090230.
[37] S. Srivastava, P. Kumar, N. Mohd, A. Singh, and F. S. Gill, “A Novel Deep Learning Framework Approach for Sugarcane Disease Detection,” SN Comput. Sci., vol. 1, no. 2, p. 87, 2020, doi: 10.1007/s42979-020-0094-9.
[38] H. S. Malik et al., “Disease Recognition in Sugarcane Crop Using Deep Learning,” Advances in Intelligent Systems and Computing, vol. 1133, no. September, pp. 189–206, 2021, doi: 10.1007/978-981-15-3514-7_17.
[39] S. Öğrekçi, Y. Ünal, and M. N. Dudak, “A comparative study of vision transformers and convolutional neural networks: sugarcane leaf diseases identification,” European Food Research and Technology, vol. 249, no. 7, pp. 1833–1843, 2023, doi: 10.1007/s00217-023-04258-1.
[40] K. J. Kavitha and K. Krishna Prasad, “CNN ensemble approach for early detection of sugarcane diseases – a comparison,” International Journal of Electronics and Telecommunications, vol. 70, no. 2, pp. 455–464, 2024, doi: 10.24425/ijet.2024.149566.
[41] S. D. Daphal and S. M. Koli, “Enhanced deep learning technique for sugarcane leaf disease classification and mobile application integration,” Heliyon, vol. 10, no. 8, p. e29438, 2024, doi: 10.1016/j.heliyon.2024.e29438.
[42] Y. Huang, R. Li, X. Wei, Z. Wang, T. Ge, and X. Qiao, “Evaluating Data Augmentation Effects on the Recognition of Sugarcane Leaf Spot,” 2022.
[43] İ. Kunduracıoğlu and İ. Paçal, “Deep Learning-Based Disease Detection in Sugarcane Leaves: Evaluating EfficientNet Models,” Journal of Operations Intelligence, vol. 2, no. 1, pp. 321–235, 2024, doi: 10.31181/jopi21202423.
[44] M. F. Shahid, T. J. S. Khanzada, M. A. Aslam, S. Hussain, S. A. Baowidan, and R. B. Ashari, “An ensemble deep learning models approach using image analysis for cotton crop classification in AI-enabled smart agriculture,” Plant Methods, vol. 20, no. 1, pp. 1–22, 2024, doi: 10.1186/s13007-024-01228-w.
[45] A. H. Ali, A. Youssef, M. Abdelal, and M. A. Raja, “An ensemble of deep learning architectures for accurate plant disease classification,” Ecol. Inform., vol. 81, p. 102618, 2024, doi: https://doi.org/10.1016/j.ecoinf.2024.102618.
[46] J. Chen, A. Zeb, Y. A. Nanehkaran, and D. Zhang, “Stacking ensemble model of deep learning for plant disease recognition,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 9, pp. 12359–12372, 2023.
[47] M. Astani, M. Hasheminejad, and M. Vaghefi, “A diverse ensemble classifier for tomato disease recognition,” Comput. Electron. Agric., vol. 198, p. 107054, 2022.
[48] Y. Lu, D. Chen, E. Olaniyi, and Y. Huang, “Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review,” Comput. Electron. Agric., vol. 200, p. 107208, 2022, doi: https://doi.org/10.1016/j.compag.2022.107208.
[49] H. Touvron, A. Vedaldi, M. Douze, and H. Jégou, “Fixing the train-test resolution discrepancy,” Adv. Neural Inf. Process. Syst., vol. 32, 2019.
[50] S. Liu and D. Huang, “Receptive field block net for accurate and fast object detection,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 385–400.
[51] L. Sun, J. He, and L. Zhang, “CASF-MNet: multi-scale network with cross attention mechanism and spatial dimension feature fusion for maize leaf disease detection,” Crop Protection, vol. 180, p. 106667, 2024.
[52] M. Brahimi, M. Arsenovic, S. Laraba, S. Sladojevic, K. Boukhalfa, and A. Moussaoui, “Deep learning for plant diseases: detection and saliency map visualisation,” Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, pp. 93–117, 2018.
[53] P. Foret, A. Kleiner, H. Mobahi, and B. Neyshabur, “Sharpness-aware minimization for efficiently improving generalization,” arXiv preprint arXiv:2010.01412, 2020.
[54] P. Izmailov, D. Podoprikhin, T. Garipov, D. Vetrov, and A. G. Wilson, “Averaging weights leads to wider optima and better generalization,” arXiv preprint arXiv:1803.05407, 2018.
[55] I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” arXiv preprint arXiv:1711.05101, 2017.
[56] G. Wang, W. Li, M. Aertsen, J. Deprest, S. Ourselin, and T. Vercauteren, “Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks,” Neurocomputing, vol. 338, pp. 34–45, 2019, doi: https://doi.org/10.1016/j.neucom.2019.01.103.
[57] D. Shanmugam, D. Blalock, G. Balakrishnan, and J. Guttag, “Better aggregation in test-time augmentation,” in Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 1214–1223.
[58] Z. Liu, Q. Wu, Y. Chai, and H. Yu, “Test-Time Adaptation of a Multi-Class Object Localization and Size Estimation Framework for Smart Agriculture Applications,” Cognit. Comput., vol. 17, no. 4, p. 132, 2025, doi: 10.1007/s12559-025-10488-0.
[59] A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, “Albumentations: Fast and Flexible Image Augmentations,” 2020. doi: 10.3390/info11020125.
[60] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal Loss for Dense Object Detection,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2999–3007. doi: 10.1109/ICCV.2017.324.
[61] S. Thite, Y. Suryawanshi, K. Patil, and P. Chumchu, “Sugarcane Leaf Dataset,” 2023, Elsevier. doi: 10.17632/355y629ynj.1.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Gautam Kumar, Vivek Bhatnagar
This work is licensed under a Creative Commons Attribution 4.0 International License.
