Performance Comparison of EfficientNet-B5, B6, and B7 for Rice Plant Disease Classification
DOI:
https://doi.org/10.57152/malcom.v6i4.2915Keywords:
Deep Learning, Disease Classification, EfficientNet, Paddy Leaf, Transfer LearningAbstract
Rapid and accurate paddy disease identification is essential for food security. This study compares EfficientNetB5, B6, and B7 for classifying paddy leaf diseases using transfer learning with the native squeeze-and-excitation blocks inherent to the EfficientNet architecture. The dataset comprised ten disease categories with 2,077 test samples, partitioned into 70% training, 15% validation, and 15% testing using stratified random sampling. EfficientNetB5 achieved the highest accuracy of 94.46%, outperforming B6 (93.89%) and B7 (91.09%). The macro average F1-score for B5 was 93.65%, followed by B6 (92.89%) and B7 (88.94%). Confusion matrices revealed B5 excelled at distinguishing visually similar symptoms, especially for bacterial leaf streak and dead heart. B7 showed the lowest performance due to overfitting from increased model complexity. Training and loss curves indicated B5 achieved the most stable convergence with minimal gap between training and validation metrics. Statistical significance testing using McNemar's test confirmed that B5's performance improvement over B7 was significant (p < 0.05), while the difference between B5 and B6 was not statistically significant. These findings prove that larger model size does not guarantee better classification performance for paddy disease recognition. EfficientNetB5 provides an optimal balance between computational efficiency and predictive accuracy
Downloads
References
R. Marco, A. H. Muhammad, N. Aini, and Y. Hendriana, “An Advanced Deep Learning Approach for Automatic Disease Recognition and Classification in paddy leaf disease detection,” Intechno Journal (Information Technology Journal), vol. 7, no. 2, pp. 86–94, Dec. 2025, doi: 10.24076/intechnojournal.2025v7i2.2482.
J. Kotwal, R. Kashyap, P. M. Shafi, and V. Kimbahune, “Enhanced leaf disease detection: UNet for segmentation and optimized EfficientNet for disease classification,” Software Impacts, vol. 22, p. 100701, Nov. 2024, doi: 10.1016/j.simpa.2024.100701.
M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proc. 36th Int. Conf. Mach. Learn., 2019, pp. 6105-6114.
J. G. Kotwal, R. Kashyap, and P. Mohd. Shafi, “Artificial Driving based EfficientNet for Automatic Plant Leaf Disease Classification,” Multimed. Tools Appl., vol. 83, no. 13, pp. 38209–38240, Oct. 2023, doi: 10.1007/s11042-023-16882-w.
F. W. Amon, B. Nath, and D. K. Bhattacharyya, “Machine learning and deep learning techniques for detecting brown spot and narrow brown spot diseases in paddy (Oryza sativa): Algorithms, challenges, and future prospects,” Inf. Sci. (N. Y)., vol. 739, p. 123195, May 2026, doi: 10.1016/j.ins.2026.123195.
H. M. Khalil, A. Elrefaiy, M. Elbaz, and A. A. Elsonbaty, “Enhanced paddy leaf disease detection using novel dual metaheuristic loss functions in generative adversarial networks with identity block preservation for thermal image augmentation,” Sci. Rep., vol. 16, no. 1, p. 6544, Feb. 2026, doi: 10.1038/s41598-026-36477-3.
C. Subbarayudu and M. Kubendiran, “An automated hybrid deep learning framework for paddy leaf disease identification and classification,” Sci. Rep., vol. 15, no. 1, p. 26873, Jul. 2025, doi: 10.1038/s41598-025-08071-6.
J. Padhi, K. Mishra, A. K. Ratha, S. K. Behera, P. K. Sethy, and A. Nanthaamornphong, “Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging,” Smart Agricultural Technology, vol. 10, p. 100814, Mar. 2025, doi: 10.1016/j.atech.2025.100814.
D. A. Nggego, M. Hasbi, and N. Patawaran, “Data augmentation and transfer learning efficientnetv2-s on rice leaf disease classification,” IOP Conf. Ser. Earth Environ. Sci., vol. 1454, no. 1, p. 012001, Feb. 2025, doi: 10.1088/1755-1315/1454/1/012001.
T. W. Utami, M. Novita, and K. Latifa, “Implementation and Comparative Analysis of CNN and Transfer Learning Models (EfficientNetB0, MobileNetV2, and ResNet50) for Rice Leaf Disease Detection Based on Digital Images,” Journal of Applied Informatics and Computing, vol. 9, no. 6, pp. 3862–3870, Dec. 2025, doi: 10.30871/jaic.v9i6.11616.
Y. Chimate, S. Patil, K. Prathapan, J. Patil, and J. Khot, “Optimized sequential model for superior classification of plant disease,” Sci. Rep., vol. 15, no. 1, p. 3700, Jan. 2025, doi: 10.1038/s41598-025-86427-8.
S. Butsianto and A. M. Rifa’i, “Tomato leaf disease classification using DenseNet-121 with data augmentation and fine-tuning,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 15, no. 3, p. 2521, Jun. 2026, doi: 10.11591/ijai.v15.i3.pp2521-2532.
C. G. Simhadri, H. K. Kondaveeti, V. K. Vatsavayi, A. Mitra, and P. Ananthachari, “Deep learning for rice leaf disease detection: A systematic literature review on emerging trends, methodologies and techniques,” Information Processing in Agriculture, vol. 12, no. 2, pp. 151–168, Jun. 2025, doi: 10.1016/j.inpa.2024.04.006.
R. Jain, S. Bekele, D. Palaniappan, K. Parmar, and P. T, “Employing Deep Convolutional Neural Networks for Enhanced Precision in Potato and Maize Leaf Disease Detection and Classification,” Turkish Journal of Engineering, vol. 9, no. 2, pp. 290–301, Jun. 2025, doi: 10.31127/tuje.1581124.
M. Guzel, B. Turan, I. Kadioglu, B. Sin, A. Basturk, and K. R. Ahmed, “How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning,” Turkish Journal of Agriculture - Food Science and Technology, vol. 10, no. 8, pp. 1441–1446, Aug. 2022, doi: 10.24925/turjaf.v10i8.1441-1446.5183.
M. Fitriyasari, “Tren dan Tantangan Deep Learning untuk Identifikasi Penyakit Daun Padi: Tinjauan Literatur Sistematis,” SATESI: Jurnal Sains Teknologi dan Sistem Informasi, vol. 6, no. 1, pp. 60–69, 2026.
N. Liu, Q. Zhao, R. Williams, S.-B. Duan, Y. Sun, and B. Barrett, “Ensemble modelling based on transfer learning for enhancing crop mapping through synergistic integration of InSAR coherence and multispectral satellite data,” Comput. Electron. Agric., vol. 242, p. 111332, Feb. 2026, doi: 10.1016/j.compag.2025.111332.
S. N. Yousafzai et al., “Advanced clustering and transfer learning based approach for rice leaf disease segmentation and classification,” PeerJ Comput. Sci., vol. 11, p. e3018, Jul. 2025, doi: 10.7717/peerj-cs.3018.
M. Purba, “Classification of Rice Leaf Diseases and Pests Using the ResNet50 Model on the AgroGuard AI Dataset,” JSAI (Journal Scientific and Applied Informatics), vol. 9, no. 1, pp. 179–185, Jan. 2026, doi: 10.36085/jsai.v9i1.9987.
S. Kanakala and S. Ningappa, “Detection and Classification of Diseases in Multi-Crop Leaves using LSTM and CNN Models,” Apr. 2025, Accessed: Jun. 12, 2026. [Online]. Available: https://arxiv.org/abs/2505.00741
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Shifa Oktifyanindar, Maman Somantri, R Rizal Isnanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
