Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention
Accurate classification of moss species is essential for progress in ecology and biology. However, traditional methods for classifying moss require significant expertise, and current deep learning techniques struggle due to limited dataset diversity and poor performance in multi-class classification...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10496696/ |
| _version_ | 1797201296183263232 |
|---|---|
| author | Peichen Li Huiqin Wang Zhan Wang Ke Wang Chong Wang |
| author_facet | Peichen Li Huiqin Wang Zhan Wang Ke Wang Chong Wang |
| author_sort | Peichen Li |
| collection | DOAJ |
| description | Accurate classification of moss species is essential for progress in ecology and biology. However, traditional methods for classifying moss require significant expertise, and current deep learning techniques struggle due to limited dataset diversity and poor performance in multi-class classification tasks. To overcome these challenges, we proposed the Swin Routiformer, a new algorithm for moss image classification that enhances the Swin Transformer with bi-level routing attention. Addressing the issue of limited data, we constructed a dataset with images of 110 different moss types. Additionally, we propose the Crop-Similar data augmentation algorithm, specifically designed for moss images, to reduce background noise interference and prevent information loss due to feature scaling. Adopting the Swin Transformer model with its multi-level hierarchical architecture for visual feature extraction, we introduce the Swin Routiformer Block, which enhances the network’s feature interaction capabilities, reduces computational complexity, and improves classification accuracy and image processing speed for moss species. Our experimental results show that the Swin Routiformer achieves a top-1 accuracy of 82.19% and an f1-score of 82.79% on the test set, outperforming most mainstream models by 4.53% and 1.81% respectively compared to the baseline Swin Transformer model. These findings establish the Swin Routiformer as a valuable tool for the precise identification of moss species, offering significant contributions to the related fields. |
| first_indexed | 2024-04-24T07:45:17Z |
| format | Article |
| id | doaj.art-043dde3c7d9b40e695870ed89bc6f1c9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T07:45:17Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-043dde3c7d9b40e695870ed89bc6f1c92024-04-18T23:00:48ZengIEEEIEEE Access2169-35362024-01-0112533965340710.1109/ACCESS.2024.338754110496696Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing AttentionPeichen Li0https://orcid.org/0009-0000-5051-2168Huiqin Wang1Zhan Wang2Ke Wang3Chong Wang4School of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaSchool of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaShaanxi Institute for the Preservation of Cultural Heritage, Xi’an, Shaanxi, ChinaSchool of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an, Shaanxi, ChinaShaanxi Institute for the Preservation of Cultural Heritage, Xi’an, Shaanxi, ChinaAccurate classification of moss species is essential for progress in ecology and biology. However, traditional methods for classifying moss require significant expertise, and current deep learning techniques struggle due to limited dataset diversity and poor performance in multi-class classification tasks. To overcome these challenges, we proposed the Swin Routiformer, a new algorithm for moss image classification that enhances the Swin Transformer with bi-level routing attention. Addressing the issue of limited data, we constructed a dataset with images of 110 different moss types. Additionally, we propose the Crop-Similar data augmentation algorithm, specifically designed for moss images, to reduce background noise interference and prevent information loss due to feature scaling. Adopting the Swin Transformer model with its multi-level hierarchical architecture for visual feature extraction, we introduce the Swin Routiformer Block, which enhances the network’s feature interaction capabilities, reduces computational complexity, and improves classification accuracy and image processing speed for moss species. Our experimental results show that the Swin Routiformer achieves a top-1 accuracy of 82.19% and an f1-score of 82.79% on the test set, outperforming most mainstream models by 4.53% and 1.81% respectively compared to the baseline Swin Transformer model. These findings establish the Swin Routiformer as a valuable tool for the precise identification of moss species, offering significant contributions to the related fields.https://ieeexplore.ieee.org/document/10496696/Moss classificationdeep learningattention mechanismimage classificationswin transformer |
| spellingShingle | Peichen Li Huiqin Wang Zhan Wang Ke Wang Chong Wang Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention IEEE Access Moss classification deep learning attention mechanism image classification swin transformer |
| title | Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention |
| title_full | Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention |
| title_fullStr | Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention |
| title_full_unstemmed | Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention |
| title_short | Swin Routiformer: Moss Classification Algorithm Based on Swin Transformer With Bi-Level Routing Attention |
| title_sort | swin routiformer moss classification algorithm based on swin transformer with bi level routing attention |
| topic | Moss classification deep learning attention mechanism image classification swin transformer |
| url | https://ieeexplore.ieee.org/document/10496696/ |
| work_keys_str_mv | AT peichenli swinroutiformermossclassificationalgorithmbasedonswintransformerwithbilevelroutingattention AT huiqinwang swinroutiformermossclassificationalgorithmbasedonswintransformerwithbilevelroutingattention AT zhanwang swinroutiformermossclassificationalgorithmbasedonswintransformerwithbilevelroutingattention AT kewang swinroutiformermossclassificationalgorithmbasedonswintransformerwithbilevelroutingattention AT chongwang swinroutiformermossclassificationalgorithmbasedonswintransformerwithbilevelroutingattention |