Best Representation Branch Model for Remote Sensing Image Scene Classification
Remote sensing image scene classification is an important method for understanding the high-resolution remote sensing images. Based on convolutional neural network, various classification methods have been applied into this field and achieved remarkable results. These methods mainly rely on the sema...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9546686/ |
| _version_ | 1818055047343243264 |
|---|---|
| author | Xinqi Zhang Weining An Jinggong Sun Hang Wu Wenchang Zhang Yaohua Du |
| author_facet | Xinqi Zhang Weining An Jinggong Sun Hang Wu Wenchang Zhang Yaohua Du |
| author_sort | Xinqi Zhang |
| collection | DOAJ |
| description | Remote sensing image scene classification is an important method for understanding the high-resolution remote sensing images. Based on convolutional neural network, various classification methods have been applied into this field and achieved remarkable results. These methods mainly rely on the semantic information to improve the classification performance. However, as the network goes deeper, the highly abstract and global semantic information makes it difficult for the network to accurately classify scene images with similar layout and structures, limiting further improvement of classification accuracy. Relying on the semantic information only is not sufficient to effectively classify these similar scene images and the network needs spatial information to enhance the classification capability. To solve this dilemma, this article proposes a best representation branch model, which reaches the optimal balance point where the network can make use of both the semantic information and spatial information to improve the final classification accuracy. In the proposed method, ResNet50 pretrained on the ImageNet dataset is first divided into four branches with different depths to extract feature maps and a capsule network is used as the classifier. The Grad-CAM algorithm is adopted to explain the mechanism of the optimal balance point from the perspective of attention and guide the further feature fusion. In addition, ablation studies are conducted to prove the effectiveness of our method and extensive experiments are conducted on three public benchmark remote sensing datasets. The results demonstrate that the proposed method can achieve competitive classification performance compared to the state-of-the-art methods. |
| first_indexed | 2024-12-10T12:06:44Z |
| format | Article |
| id | doaj.art-58c731d3984140ab8211d88d55713996 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-10T12:06:44Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-58c731d3984140ab8211d88d557139962022-12-22T01:49:27ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01149768978010.1109/JSTARS.2021.31144049546686Best Representation Branch Model for Remote Sensing Image Scene ClassificationXinqi Zhang0https://orcid.org/0000-0002-2142-4297Weining An1Jinggong Sun2Hang Wu3https://orcid.org/0000-0002-6000-8026Wenchang Zhang4Yaohua Du5Research Department of Medical Support Technology, Academy of Military Science, Tianjin, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin, ChinaInstitute of System Engineering, Academy of Military Science, Beijing, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin, ChinaRemote sensing image scene classification is an important method for understanding the high-resolution remote sensing images. Based on convolutional neural network, various classification methods have been applied into this field and achieved remarkable results. These methods mainly rely on the semantic information to improve the classification performance. However, as the network goes deeper, the highly abstract and global semantic information makes it difficult for the network to accurately classify scene images with similar layout and structures, limiting further improvement of classification accuracy. Relying on the semantic information only is not sufficient to effectively classify these similar scene images and the network needs spatial information to enhance the classification capability. To solve this dilemma, this article proposes a best representation branch model, which reaches the optimal balance point where the network can make use of both the semantic information and spatial information to improve the final classification accuracy. In the proposed method, ResNet50 pretrained on the ImageNet dataset is first divided into four branches with different depths to extract feature maps and a capsule network is used as the classifier. The Grad-CAM algorithm is adopted to explain the mechanism of the optimal balance point from the perspective of attention and guide the further feature fusion. In addition, ablation studies are conducted to prove the effectiveness of our method and extensive experiments are conducted on three public benchmark remote sensing datasets. The results demonstrate that the proposed method can achieve competitive classification performance compared to the state-of-the-art methods.https://ieeexplore.ieee.org/document/9546686/Best representation branch modeldeep learning (DL)remote sensing (RS) imagespatial information |
| spellingShingle | Xinqi Zhang Weining An Jinggong Sun Hang Wu Wenchang Zhang Yaohua Du Best Representation Branch Model for Remote Sensing Image Scene Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Best representation branch model deep learning (DL) remote sensing (RS) image spatial information |
| title | Best Representation Branch Model for Remote Sensing Image Scene Classification |
| title_full | Best Representation Branch Model for Remote Sensing Image Scene Classification |
| title_fullStr | Best Representation Branch Model for Remote Sensing Image Scene Classification |
| title_full_unstemmed | Best Representation Branch Model for Remote Sensing Image Scene Classification |
| title_short | Best Representation Branch Model for Remote Sensing Image Scene Classification |
| title_sort | best representation branch model for remote sensing image scene classification |
| topic | Best representation branch model deep learning (DL) remote sensing (RS) image spatial information |
| url | https://ieeexplore.ieee.org/document/9546686/ |
| work_keys_str_mv | AT xinqizhang bestrepresentationbranchmodelforremotesensingimagesceneclassification AT weiningan bestrepresentationbranchmodelforremotesensingimagesceneclassification AT jinggongsun bestrepresentationbranchmodelforremotesensingimagesceneclassification AT hangwu bestrepresentationbranchmodelforremotesensingimagesceneclassification AT wenchangzhang bestrepresentationbranchmodelforremotesensingimagesceneclassification AT yaohuadu bestrepresentationbranchmodelforremotesensingimagesceneclassification |