Comparative Analysis of MambaOut Tiny and Vision Transformer for Corn Leaf Disease Classification

Adi Slamet Priyadi; Albert Yakobus Chandra

doi:10.55537/cosie.v5i3.1834

Authors

Adi Slamet Priyadi Universitas Mercu Buana Yogyakarta
Albert Yakobus Chandra Universitas Mercu Buana Yogyakarta

DOI:

https://doi.org/10.55537/cosie.v5i3.1834

Keywords:

Vision Transformer, MambaOut Tiny, Deep Learning, orn Leaf Disease Classification, Computer Vision, Artificial Intelligence

Abstract

Maize production remains vulnerable to foliar diseases such as Gray Leaf Spot, Common Rust, and Northern Leaf Blight, which can impair growth and reduce crop yields. Manual disease identification is time-consuming, labor-intensive, and reliant on the observer's expertise, necessitating automated detection systems based on deep learning. While Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are widely used for plant disease classification, a direct comparison between ViT-B/16 and MambaOut Tiny under identical training conditions remains rare. This study compares the two models using the PlantVillage dataset, which comprises 4,188 maize leaf images across four classes. Both models were fine-tuned using ImageNet-1K pre-trained weights, the AdamW optimizer, a learning rate of 1e-4, a batch size of 16, and 10 epochs. The results demonstrate that MambaOut Tiny achieved an accuracy of 97% and a macro-average F1-score of 0.96, outperforming ViT-B/16, which achieved 95% accuracy and an F1-score of 0.93. Additionally, MambaOut Tiny features a lower parameter count (30 million versus 86 million) and faster inference time (0.01262 seconds per image). These findings indicate that MambaOut Tiny is more efficient for precision agriculture systems with limited computational resources

Downloads

Download data is not yet available.

References

[1] F. Khan, N. Zafar, M. N. Tahir, M. Aqib, H. Waheed, and Z. Haroon, “A mobile-based system for maize plant leaf disease detection and classification using deep learning,” Front. Plant Sci., vol. 14, no. May, pp. 1–18, May 2023, doi: 10.3389/fpls.2023.1079366.

[2] M. Fraiwan, E. Faouri, and N. Khasawneh, “Classification of Corn Diseases from Leaf Images Using Deep Transfer Learning,” Plants, vol. 11, no. 20, pp. 1–14, 2022, doi: 10.3390/plants11202668.

[3] Y. Chen et al., “DFCANet: A Novel Lightweight Convolutional Neural Network Model for Corn Disease Identification,” Agriculture (Switzerland), vol. 12, no. 12, 2022, doi: 10.3390/agriculture12122047.

[4] M. Masood et al., “MaizeNet: A Deep Learning Approach for Effective Recognition of Maize Plant Leaf Diseases,” IEEE Access, vol. 11, no. May, pp. 52862–52876, 2023, doi: 10.1109/ACCESS.2023.3280260.

[5] A. Tabbakh and S. S. Barpanda, “A Deep Features Extraction Model Based on the Transfer Learning Model and Vision Transformer ‘TLMViT’ for Plant Disease Classification,” IEEE Access, vol. 11, no. May, pp. 45377–45392, 2023, doi: 10.1109/ACCESS.2023.3273317.

[6] S. Jia, G. Wang, H. Li, Y. Liu, L. Shi, and S. Yang, “ConvTransNet-S: A CNN-Transformer Hybrid Disease Recognition Model for Complex Field Environments,” Plants, vol. 14, no. 15, pp. 1–17, 2025, doi: 10.3390/plants14152252.

[7] Q. Meng, J. Guo, H. Zhang, Y. Zhou, and X. Zhang, “A dual-branch model combining convolution and vision transformer for crop disease classification,” PLoS One, vol. 20, no. 4 April, pp. 1–23, 2025, doi: 10.1371/journal.pone.0321753.

[8] X. Li and S. Li, “Transformer Help CNN See Better: A Lightweight Hybrid Apple Disease Identification Model Based on Transformers,” Agriculture (Switzerland), vol. 12, no. 6, 2022, doi: 10.3390/agriculture12060884.

[9] A. Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” ICLR 2021 - 9th International Conference on Learning Representations, Jun. 2021, [Online]. Available: http://arxiv.org/abs/2010.11929

[10] Y. Borhani, J. Khoramdel, and E. Najafi, “A deep learning based approach for automated plant disease classification using vision transformer,” Sci. Rep., vol. 12, no. 1, pp. 1–10, 2022, doi: 10.1038/s41598-022-15163-0.

[11] S. Aboelenin, F. A. Elbasheer, M. M. Eltoukhy, W. M. El-Hady, and K. M. Hosny, “A hybrid Framework for plant leaf disease detection and classification using convolutional neural networks and vision transformer,” Complex and Intelligent Systems, vol. 11, no. 2, 2025, doi: 10.1007/s40747-024-01764-x.

[12] S. Murugavalli and R. Gopi, “Plant leaf disease detection using vision transformers for precision agriculture,” Sci. Rep., vol. 15, no. 1, pp. 1–17, 2025, doi: 10.1038/s41598-025-05102-0.

[13] M. De Silva and D. Brown, “Multispectral Plant Disease Detection with Vision Transformer-Convolutional Neural Network Hybrid Approaches,” Sensors (Basel), vol. 23, no. 20, 2023, doi: 10.3390/s23208531.

[14] K. Chen, B. Chen, C. Liu, W. Li, Z. Zou, and Z. Shi, “RSMamba: Remote Sensing Image Classification with State Space Model,” IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1–5, 2024, doi: 10.1109/LGRS.2024.3407111.

[15] E. T. Baek, “Attention Score-Based Multi-Vision Transformer Technique for Plant Disease Classification,” Sensors, vol. 25, no. 1, 2025, doi: 10.3390/s25010270.

[16] P. S. Thakur, P. Khanna, T. Sheorey, and A. Ojha, “Explainable vision transformer enabled convolutional neural network for plant disease identification: PlantXViT,” no. Dl, Jul. 2022, [Online]. Available: http://arxiv.org/abs/2207.07919

[17] B. Hu, W. Jiang, J. Zeng, C. Cheng, and L. He, “FOTCA: hybrid transformer-CNN architecture using AFNO for accurate plant leaf disease image recognition,” Front. Plant Sci., vol. 14, no. September, pp. 1–12, 2023, doi: 10.3389/fpls.2023.1231903.

[18] A. Gu and T. Dao, “Mamba: Linear-Time Sequence Modeling with Selective State Spaces,” no. Kalman 1960, pp. 1–36, May 2024, [Online]. Available: http://arxiv.org/abs/2312.00752

[19] L. Zhu, B. Liao, Q. Zhang, X. Wang, W. Liu, and X. Wang, “Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model,” Proc. Mach. Learn. Res., vol. 235, pp. 62429–62442, Nov. 2024, [Online]. Available: http://arxiv.org/abs/2401.09417

[20] Y. Liu et al., “VMamba: Visual State Space Model,” in Advances in Neural Information Processing Systems 37, San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2024, pp. 103031–103063. doi: 10.52202/079017-3273.

[21] W. Yu and X. Wang, “MambaOut: Do We Really Need Mamba for Vision?,” in 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Jun. 2025, pp. 4484–4496. doi: 10.1109/CVPR52734.2025.00423.

[22] Y. Yue and Z. Li, “MedMamba: Vision Mamba for Medical Image Classification,” Sep. 2024, [Online]. Available: http://arxiv.org/abs/2403.03849

[23] H. Zhang, S. Li, J. Xie, Z. Chen, J. Chen, and J. Guo, “VMamba for plant leaf disease identification: design and experiment,” Front. Plant Sci., vol. 16, no. April, pp. 1–17, 2025, doi: 10.3389/fpls.2025.1515021.

[24] I. Kunduracioglu and I. Pacal, “Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases,” Journal of Plant Diseases and Protection, vol. 131, no. 3, pp. 1061–1080, 2024, doi: 10.1007/s41348-024-00896-z.

[25] F. Zhuang et al., “A Comprehensive Survey on Transfer Learning,” Proceedings of the IEEE, vol. 109, no. 1, pp. 43–76, Jan. 2021, doi: 10.1109/JPROC.2020.3004555.

[26] A. Tharwat, “Classification assessment methods,” Applied Computing and Informatics, vol. 17, no. 1, pp. 168–192, 2018, doi: 10.1016/j.aci.2018.08.003.