Spectral Swin Transformer Network for Hyperspectral Image Classification
Hyperspectral images are complex images that contain more spectral dimension information than ordinary images. An increasing number of HSI classification methods are using deep learning techniques to process three-dimensional data. The Vision Transformer model is gradually occupying an important pos...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/15/3721 |
| _version_ | 1797586068503003136 |
|---|---|
| author | Baisen Liu Yuanjia Liu Wulin Zhang Yiran Tian Weili Kong |
| author_facet | Baisen Liu Yuanjia Liu Wulin Zhang Yiran Tian Weili Kong |
| author_sort | Baisen Liu |
| collection | DOAJ |
| description | Hyperspectral images are complex images that contain more spectral dimension information than ordinary images. An increasing number of HSI classification methods are using deep learning techniques to process three-dimensional data. The Vision Transformer model is gradually occupying an important position in the field of computer vision and is being used to replace the CNN structure of the network. However, it is still in the preliminary research stage in the field of HSI. In this paper, we propose using a spectral Swin Transformer network for HSI classification, providing a new approach for the HSI field. The Swin Transformer uses group attention to enhance feature representation, and the sliding window attention calculation can take into account the contextual information of different windows, which can retain the global features of HSI and improve classification results. In our experiments, we evaluated our proposed approach on several public hyperspectral datasets and compared it with several methods. The experimental results demonstrate that our proposed model achieved test accuracies of 97.46%, 99.7%, and 99.8% on the IP, SA, and PU public HSI datasets, respectively, when using the AdamW optimizer. Our approach also shows good generalization ability when applied to new datasets. Overall, our proposed approach represents a promising direction for hyperspectral image classification using deep learning techniques. |
| first_indexed | 2024-03-11T00:18:03Z |
| format | Article |
| id | doaj.art-087560ea492145ef8f0ad025aecc3467 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:18:03Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-087560ea492145ef8f0ad025aecc34672023-11-18T23:29:55ZengMDPI AGRemote Sensing2072-42922023-07-011515372110.3390/rs15153721Spectral Swin Transformer Network for Hyperspectral Image ClassificationBaisen Liu0Yuanjia Liu1Wulin Zhang2Yiran Tian3Weili Kong4Department of Physics and Electronic Engineering, Mudanjiang Normal University, Mudanjiang 157011, ChinaDepartment of Physics and Electronic Engineering, Mudanjiang Normal University, Mudanjiang 157011, ChinaDepartment of Physics and Electronic Engineering, Mudanjiang Normal University, Mudanjiang 157011, ChinaDepartment of Physics and Electronic Engineering, Mudanjiang Normal University, Mudanjiang 157011, ChinaDepartment of Information and Communication Engineering, Harbin Engineering University, Harbin 150009, ChinaHyperspectral images are complex images that contain more spectral dimension information than ordinary images. An increasing number of HSI classification methods are using deep learning techniques to process three-dimensional data. The Vision Transformer model is gradually occupying an important position in the field of computer vision and is being used to replace the CNN structure of the network. However, it is still in the preliminary research stage in the field of HSI. In this paper, we propose using a spectral Swin Transformer network for HSI classification, providing a new approach for the HSI field. The Swin Transformer uses group attention to enhance feature representation, and the sliding window attention calculation can take into account the contextual information of different windows, which can retain the global features of HSI and improve classification results. In our experiments, we evaluated our proposed approach on several public hyperspectral datasets and compared it with several methods. The experimental results demonstrate that our proposed model achieved test accuracies of 97.46%, 99.7%, and 99.8% on the IP, SA, and PU public HSI datasets, respectively, when using the AdamW optimizer. Our approach also shows good generalization ability when applied to new datasets. Overall, our proposed approach represents a promising direction for hyperspectral image classification using deep learning techniques.https://www.mdpi.com/2072-4292/15/15/3721hyperspectral image classificationdeep learningSwin Transformer |
| spellingShingle | Baisen Liu Yuanjia Liu Wulin Zhang Yiran Tian Weili Kong Spectral Swin Transformer Network for Hyperspectral Image Classification Remote Sensing hyperspectral image classification deep learning Swin Transformer |
| title | Spectral Swin Transformer Network for Hyperspectral Image Classification |
| title_full | Spectral Swin Transformer Network for Hyperspectral Image Classification |
| title_fullStr | Spectral Swin Transformer Network for Hyperspectral Image Classification |
| title_full_unstemmed | Spectral Swin Transformer Network for Hyperspectral Image Classification |
| title_short | Spectral Swin Transformer Network for Hyperspectral Image Classification |
| title_sort | spectral swin transformer network for hyperspectral image classification |
| topic | hyperspectral image classification deep learning Swin Transformer |
| url | https://www.mdpi.com/2072-4292/15/15/3721 |
| work_keys_str_mv | AT baisenliu spectralswintransformernetworkforhyperspectralimageclassification AT yuanjialiu spectralswintransformernetworkforhyperspectralimageclassification AT wulinzhang spectralswintransformernetworkforhyperspectralimageclassification AT yirantian spectralswintransformernetworkforhyperspectralimageclassification AT weilikong spectralswintransformernetworkforhyperspectralimageclassification |