Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification
This paper proposes a network structure called CAMP-Net, which considers the problem that traditional deep learning algorithms are unable to manage the pixel information of different bands, resulting in poor differentiation of feature representations of different categories and causing classificatio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/16/3924 |
| _version_ | 1797583381984182272 |
|---|---|
| author | Xiangsuo Fan Xuyang Li Chuan Yan Jinlong Fan Lin Chen Nayi Wang |
| author_facet | Xiangsuo Fan Xuyang Li Chuan Yan Jinlong Fan Lin Chen Nayi Wang |
| author_sort | Xiangsuo Fan |
| collection | DOAJ |
| description | This paper proposes a network structure called CAMP-Net, which considers the problem that traditional deep learning algorithms are unable to manage the pixel information of different bands, resulting in poor differentiation of feature representations of different categories and causing classification overfitting. CAMP-Net is a parallel network that, firstly, enhances the interaction of local information of bands by grouping the spectral nesting of the band information and then proposes a parallel processing model. One branch is responsible for inputting the features, normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) band information generated by grouped nesting into the ViT framework, and enhancing the interaction and information flow between different channels in the feature map by adding the channel attention mechanism to realize the expressive capability of the feature map. The other branch assists the network’s ability to enhance the extraction of different feature channels by designing a multi-layer perceptron network based on the utilization of the feature channels. Finally, the classification results are obtained by fusing the features obtained by the channel attention mechanism with those obtained by the MLP to achieve pixel-level multispectral image classification. In this study, the application of the algorithm was carried out in the feature distribution of South County, Yiyang City, Hunan Province, and the experiments were conducted based on 10 m Sentinel-2 multispectral RS images. The experimental results show that the overall accuracy of the algorithm proposed in this paper is 99.00% and the transformer (ViT) is 95.81%, while the performance of the algorithm in the Sentinel-2 dataset was greatly improved for the transformer. The transformer shows a huge improvement, which provides research value for developing a land cover classification algorithm for remote sensing images. |
| first_indexed | 2024-03-10T23:38:10Z |
| format | Article |
| id | doaj.art-f96bb3edf0274c469b91f890d92f11d3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:38:10Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f96bb3edf0274c469b91f890d92f11d32023-11-19T02:52:02ZengMDPI AGRemote Sensing2072-42922023-08-011516392410.3390/rs15163924Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover ClassificationXiangsuo Fan0Xuyang Li1Chuan Yan2Jinlong Fan3Lin Chen4Nayi Wang5School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou 545006, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou 545006, ChinaNational Satellite Meteorological Center, China Meteorological Administration, Beijing 100081, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou 545006, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou 545006, ChinaThis paper proposes a network structure called CAMP-Net, which considers the problem that traditional deep learning algorithms are unable to manage the pixel information of different bands, resulting in poor differentiation of feature representations of different categories and causing classification overfitting. CAMP-Net is a parallel network that, firstly, enhances the interaction of local information of bands by grouping the spectral nesting of the band information and then proposes a parallel processing model. One branch is responsible for inputting the features, normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) band information generated by grouped nesting into the ViT framework, and enhancing the interaction and information flow between different channels in the feature map by adding the channel attention mechanism to realize the expressive capability of the feature map. The other branch assists the network’s ability to enhance the extraction of different feature channels by designing a multi-layer perceptron network based on the utilization of the feature channels. Finally, the classification results are obtained by fusing the features obtained by the channel attention mechanism with those obtained by the MLP to achieve pixel-level multispectral image classification. In this study, the application of the algorithm was carried out in the feature distribution of South County, Yiyang City, Hunan Province, and the experiments were conducted based on 10 m Sentinel-2 multispectral RS images. The experimental results show that the overall accuracy of the algorithm proposed in this paper is 99.00% and the transformer (ViT) is 95.81%, while the performance of the algorithm in the Sentinel-2 dataset was greatly improved for the transformer. The transformer shows a huge improvement, which provides research value for developing a land cover classification algorithm for remote sensing images.https://www.mdpi.com/2072-4292/15/16/3924CAMP-Netland usechannel attentionmultilayer perceptronparallel networks |
| spellingShingle | Xiangsuo Fan Xuyang Li Chuan Yan Jinlong Fan Lin Chen Nayi Wang Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification Remote Sensing CAMP-Net land use channel attention multilayer perceptron parallel networks |
| title | Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification |
| title_full | Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification |
| title_fullStr | Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification |
| title_full_unstemmed | Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification |
| title_short | Converging Channel Attention Mechanisms with Multilayer Perceptron Parallel Networks for Land Cover Classification |
| title_sort | converging channel attention mechanisms with multilayer perceptron parallel networks for land cover classification |
| topic | CAMP-Net land use channel attention multilayer perceptron parallel networks |
| url | https://www.mdpi.com/2072-4292/15/16/3924 |
| work_keys_str_mv | AT xiangsuofan convergingchannelattentionmechanismswithmultilayerperceptronparallelnetworksforlandcoverclassification AT xuyangli convergingchannelattentionmechanismswithmultilayerperceptronparallelnetworksforlandcoverclassification AT chuanyan convergingchannelattentionmechanismswithmultilayerperceptronparallelnetworksforlandcoverclassification AT jinlongfan convergingchannelattentionmechanismswithmultilayerperceptronparallelnetworksforlandcoverclassification AT linchen convergingchannelattentionmechanismswithmultilayerperceptronparallelnetworksforlandcoverclassification AT nayiwang convergingchannelattentionmechanismswithmultilayerperceptronparallelnetworksforlandcoverclassification |