Hybrid Vision Mamba Transformer Network for Accurate Tomato Leaf Disease Classification
Keywords:
Tomato leaf disease classification, Vision Mamba, Vision Transformer, Deep learning, Precision agriculture, PlantVillage dataset, Hybrid neural network.Abstract
Timely identification of tomato leaf diseases can help farmers preserve yield and achieve better field management. Deep image models are able to address this problem. Convolutional neural networks perform great on local relations, while they fail to model relationships between distant regions of an image. On the other hand, Vision Transformers allow capturing the large context; however, they are quite costly in terms of computational expenses.In this study, we propose a Hybrid Vision Mamba Transformer Network, referred to as HVMTNet, to automate the tomato leaf disease detection process. The architecture utilizes various components. At first, a conv stem learns local features from an image. Next, a Vision Mamba encoder is applied to model long-range dependencies efficiently. Afterward, a Transformer encoder is used to learn broader scene context. Finally, adaptive feature fusion is performed to aggregate the learned cues and generate disease-specific features.HVMTNetis evaluated on the PlantVillage tomato leaf disease dataset. There are ten disease classes in it. The data are partitioned into subsets using 70:15:15 ratio. The proposed approach outperforms ResNet50, EfficientNet-B0, ConvNeXt-Tiny, Vision Transformer, and Vision Mamba models. The obtained results are as follows: 99.61% accuracy, 99.54% precision, 99.48% recall, 99.51% F1-score, and AUC 0.999.
Downloads
Downloads
Published
Issue
Section
License
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.

