Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images
Accurate identification of rice diseases is crucial for improving rice yield and ensuring food security. In this study, we constructed an image dataset containing six classes of rice diseases captured under real field conditions to address challenges such as complex backgrounds, varying lighting, an...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/6/571 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850205863239745536 |
|---|---|
| author | Meng Zhang Zichao Lin Shuqi Tang Chenjie Lin Liping Zhang Wei Dong Nan Zhong |
| author_facet | Meng Zhang Zichao Lin Shuqi Tang Chenjie Lin Liping Zhang Wei Dong Nan Zhong |
| author_sort | Meng Zhang |
| collection | DOAJ |
| description | Accurate identification of rice diseases is crucial for improving rice yield and ensuring food security. In this study, we constructed an image dataset containing six classes of rice diseases captured under real field conditions to address challenges such as complex backgrounds, varying lighting, and symptom similarities. Based on the MobileViT-XXS architecture, we proposed an enhanced model named MobileViT-DAP, which integrates Channel Attention (CA), Efficient Channel Attention (ECA), and PoolFormer blocks to achieve precise classification of rice diseases. The experimental results demonstrated that the improved model achieved superior performance with 0.75 M Params and 0.23 G FLOPs, ensuring computational efficiency while maintaining high classification accuracy. On the testing set, the model achieved an accuracy of 99.61%, a precision of 99.64%, a recall of 99.59%, and a specificity of 99.92%. Compared to traditional lightweight models, MobileViT-DAP showed significant improvements in model complexity, computational efficiency, and classification performance, effectively balancing lightweight design with high accuracy. Furthermore, visualization analysis confirmed that the model’s decision-making process primarily relies on lesion-related features, enhancing its interpretability and reliability. This study provides a novel perspective for optimizing plant disease recognition tasks and contributes to improving plant protection strategies, offering a solution for accurate and efficient disease monitoring in agricultural applications. |
| format | Article |
| id | doaj-art-ef78cc5b997d4f6fb6fe89ec43607ad2 |
| institution | OA Journals |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-ef78cc5b997d4f6fb6fe89ec43607ad22025-08-20T02:11:00ZengMDPI AGAgriculture2077-04722025-03-0115657110.3390/agriculture15060571Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured ImagesMeng Zhang0Zichao Lin1Shuqi Tang2Chenjie Lin3Liping Zhang4Wei Dong5Nan Zhong6College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaAgricultural Economy and Information Research Institute, Anhui Academy of Agricultural Sciences, Hefei 230031, ChinaAgricultural Economy and Information Research Institute, Anhui Academy of Agricultural Sciences, Hefei 230031, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaAccurate identification of rice diseases is crucial for improving rice yield and ensuring food security. In this study, we constructed an image dataset containing six classes of rice diseases captured under real field conditions to address challenges such as complex backgrounds, varying lighting, and symptom similarities. Based on the MobileViT-XXS architecture, we proposed an enhanced model named MobileViT-DAP, which integrates Channel Attention (CA), Efficient Channel Attention (ECA), and PoolFormer blocks to achieve precise classification of rice diseases. The experimental results demonstrated that the improved model achieved superior performance with 0.75 M Params and 0.23 G FLOPs, ensuring computational efficiency while maintaining high classification accuracy. On the testing set, the model achieved an accuracy of 99.61%, a precision of 99.64%, a recall of 99.59%, and a specificity of 99.92%. Compared to traditional lightweight models, MobileViT-DAP showed significant improvements in model complexity, computational efficiency, and classification performance, effectively balancing lightweight design with high accuracy. Furthermore, visualization analysis confirmed that the model’s decision-making process primarily relies on lesion-related features, enhancing its interpretability and reliability. This study provides a novel perspective for optimizing plant disease recognition tasks and contributes to improving plant protection strategies, offering a solution for accurate and efficient disease monitoring in agricultural applications.https://www.mdpi.com/2077-0472/15/6/571rice diseaseslightweight modeldeep learningattention mechanismvisualization |
| spellingShingle | Meng Zhang Zichao Lin Shuqi Tang Chenjie Lin Liping Zhang Wei Dong Nan Zhong Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images Agriculture rice diseases lightweight model deep learning attention mechanism visualization |
| title | Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images |
| title_full | Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images |
| title_fullStr | Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images |
| title_full_unstemmed | Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images |
| title_short | Dual-Attention-Enhanced MobileViT Network: A Lightweight Model for Rice Disease Identification in Field-Captured Images |
| title_sort | dual attention enhanced mobilevit network a lightweight model for rice disease identification in field captured images |
| topic | rice diseases lightweight model deep learning attention mechanism visualization |
| url | https://www.mdpi.com/2077-0472/15/6/571 |
| work_keys_str_mv | AT mengzhang dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages AT zichaolin dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages AT shuqitang dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages AT chenjielin dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages AT lipingzhang dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages AT weidong dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages AT nanzhong dualattentionenhancedmobilevitnetworkalightweightmodelforricediseaseidentificationinfieldcapturedimages |