SAR Target Classification Based on Multiscale Attention Super-Class Network
The convolutional neural network (CNN) is widely used in synthetic aperture radar (SAR) target recognition, but conventional CNN mainly adopts a single-scale convolutional kernel, resulting in losing part of the feature information of targets and does not pay enough attention to significant features...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9893301/ |
| _version_ | 1797985678211940352 |
|---|---|
| author | Di Wang Yongping Song Junnan Huang Daoxiang An Leping Chen |
| author_facet | Di Wang Yongping Song Junnan Huang Daoxiang An Leping Chen |
| author_sort | Di Wang |
| collection | DOAJ |
| description | The convolutional neural network (CNN) is widely used in synthetic aperture radar (SAR) target recognition, but conventional CNN mainly adopts a single-scale convolutional kernel, resulting in losing part of the feature information of targets and does not pay enough attention to significant features. On the other hand, conventional CNN approaches only assign fine-class labels to SAR targets, ignoring the high-level semantics information of similar categories, which reduces the feature differences between categories and the generalization ability of the model. Therefore, this article proposes a multiscale attention super-class CNN (MSA-SCNN) for SAR target classification. First, MSA-SCNN combines multiscale feature fusion with the attention module to improve the integrity of SAR target feature representation. The attention module includes channel and spatial attention modules, which realize the weighted enhancement of different scale features. Additionally, MSA-SCNN introduces super-class labels to increase the feature difference between categories. The classification stage consists of a fine-class branch and a super-class branch, and the features trained on the super-class branch are fused to the fine-class branch to improve the network's fine classification ability. Experiments on the moving and stationary target acquisition and recognition dataset and the FUSAR-Ship dataset show that the proposed MSA-SCNN outperforms many current existing state-of-the-art methods. |
| first_indexed | 2024-04-11T07:22:03Z |
| format | Article |
| id | doaj.art-5507720b02764b1cb28b8eb11c17d4fa |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-11T07:22:03Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-5507720b02764b1cb28b8eb11c17d4fa2022-12-22T04:37:11ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01159004901910.1109/JSTARS.2022.32069019893301SAR Target Classification Based on Multiscale Attention Super-Class NetworkDi Wang0https://orcid.org/0000-0002-4864-4097Yongping Song1https://orcid.org/0000-0003-4191-0548Junnan Huang2Daoxiang An3https://orcid.org/0000-0002-1363-9140Leping Chen4https://orcid.org/0000-0002-2742-0326College of Electronic Science, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science, National University of Defense Technology, Changsha, ChinaThe convolutional neural network (CNN) is widely used in synthetic aperture radar (SAR) target recognition, but conventional CNN mainly adopts a single-scale convolutional kernel, resulting in losing part of the feature information of targets and does not pay enough attention to significant features. On the other hand, conventional CNN approaches only assign fine-class labels to SAR targets, ignoring the high-level semantics information of similar categories, which reduces the feature differences between categories and the generalization ability of the model. Therefore, this article proposes a multiscale attention super-class CNN (MSA-SCNN) for SAR target classification. First, MSA-SCNN combines multiscale feature fusion with the attention module to improve the integrity of SAR target feature representation. The attention module includes channel and spatial attention modules, which realize the weighted enhancement of different scale features. Additionally, MSA-SCNN introduces super-class labels to increase the feature difference between categories. The classification stage consists of a fine-class branch and a super-class branch, and the features trained on the super-class branch are fused to the fine-class branch to improve the network's fine classification ability. Experiments on the moving and stationary target acquisition and recognition dataset and the FUSAR-Ship dataset show that the proposed MSA-SCNN outperforms many current existing state-of-the-art methods.https://ieeexplore.ieee.org/document/9893301/Convolutional neural network (CNN)multiscale attentionsuper-class labelssynthetic aperture radar (SAR) target classification |
| spellingShingle | Di Wang Yongping Song Junnan Huang Daoxiang An Leping Chen SAR Target Classification Based on Multiscale Attention Super-Class Network IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional neural network (CNN) multiscale attention super-class labels synthetic aperture radar (SAR) target classification |
| title | SAR Target Classification Based on Multiscale Attention Super-Class Network |
| title_full | SAR Target Classification Based on Multiscale Attention Super-Class Network |
| title_fullStr | SAR Target Classification Based on Multiscale Attention Super-Class Network |
| title_full_unstemmed | SAR Target Classification Based on Multiscale Attention Super-Class Network |
| title_short | SAR Target Classification Based on Multiscale Attention Super-Class Network |
| title_sort | sar target classification based on multiscale attention super class network |
| topic | Convolutional neural network (CNN) multiscale attention super-class labels synthetic aperture radar (SAR) target classification |
| url | https://ieeexplore.ieee.org/document/9893301/ |
| work_keys_str_mv | AT diwang sartargetclassificationbasedonmultiscaleattentionsuperclassnetwork AT yongpingsong sartargetclassificationbasedonmultiscaleattentionsuperclassnetwork AT junnanhuang sartargetclassificationbasedonmultiscaleattentionsuperclassnetwork AT daoxiangan sartargetclassificationbasedonmultiscaleattentionsuperclassnetwork AT lepingchen sartargetclassificationbasedonmultiscaleattentionsuperclassnetwork |