Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images
Fine-grained ship detection is very important in the remote sensing field. Most previous remote sensing object detection works only utilize the global features for fine-grained object detection, which ignores the local information, deteriorating the detection performance. In this article, we propose...
| 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/9942287/ |
| _version_ | 1798016968336343040 |
|---|---|
| author | Lihan Ouyang Leyuan Fang Xinyu Ji |
| author_facet | Lihan Ouyang Leyuan Fang Xinyu Ji |
| author_sort | Lihan Ouyang |
| collection | DOAJ |
| description | Fine-grained ship detection is very important in the remote sensing field. Most previous remote sensing object detection works only utilize the global features for fine-grained object detection, which ignores the local information, deteriorating the detection performance. In this article, we propose a multigranularity self-attention network (MGANet), which can exploit both the global and local features for fine-grained ship detection. The MGANet consists of two modules: a local-global features alignment module (LAM) and a multigranularity self-attention module (MSM). The LAM is designed to align features of object parts and features of the object by using the convolution with different strides. The MSM introduces a self-attention mechanism that can effectively fuse the global and local features for fine-grained ship detection. In addition, we launched an oriented bounding box-based fine-grained ship detection (OFSD) dataset which is the largest fine-grained ship dataset to test and verify the effectiveness of the proposed MGANet method. Comprehensive evaluations on the OFSD and ShipRSImageNet datasets demonstrate the superiority of our proposed MGANet method over existing state-of-the-art methods for fine-grained ship detection in remote sensing images. |
| first_indexed | 2024-04-11T15:59:27Z |
| format | Article |
| id | doaj.art-a178c846db184ae6820de7e98c9b6164 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-11T15:59:27Z |
| 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-a178c846db184ae6820de7e98c9b61642022-12-22T04:15:05ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01159722973210.1109/JSTARS.2022.32205039942287Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing ImagesLihan Ouyang0Leyuan Fang1https://orcid.org/0000-0003-2351-4461Xinyu Ji2https://orcid.org/0000-0003-1109-9766College of Electrical and Information Engineering, Hunan University, Changsha, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha, ChinaDepartment of Computing, Hong Kong Polytechnic University, Hong Kong, ChinaFine-grained ship detection is very important in the remote sensing field. Most previous remote sensing object detection works only utilize the global features for fine-grained object detection, which ignores the local information, deteriorating the detection performance. In this article, we propose a multigranularity self-attention network (MGANet), which can exploit both the global and local features for fine-grained ship detection. The MGANet consists of two modules: a local-global features alignment module (LAM) and a multigranularity self-attention module (MSM). The LAM is designed to align features of object parts and features of the object by using the convolution with different strides. The MSM introduces a self-attention mechanism that can effectively fuse the global and local features for fine-grained ship detection. In addition, we launched an oriented bounding box-based fine-grained ship detection (OFSD) dataset which is the largest fine-grained ship dataset to test and verify the effectiveness of the proposed MGANet method. Comprehensive evaluations on the OFSD and ShipRSImageNet datasets demonstrate the superiority of our proposed MGANet method over existing state-of-the-art methods for fine-grained ship detection in remote sensing images.https://ieeexplore.ieee.org/document/9942287/Deep learningfine-grained ship datasetfine-grained ship detectionmultigranularityself-attention mechanism |
| spellingShingle | Lihan Ouyang Leyuan Fang Xinyu Ji Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning fine-grained ship dataset fine-grained ship detection multigranularity self-attention mechanism |
| title | Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images |
| title_full | Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images |
| title_fullStr | Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images |
| title_full_unstemmed | Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images |
| title_short | Multigranularity Self-Attention Network for Fine-Grained Ship Detection in Remote Sensing Images |
| title_sort | multigranularity self attention network for fine grained ship detection in remote sensing images |
| topic | Deep learning fine-grained ship dataset fine-grained ship detection multigranularity self-attention mechanism |
| url | https://ieeexplore.ieee.org/document/9942287/ |
| work_keys_str_mv | AT lihanouyang multigranularityselfattentionnetworkforfinegrainedshipdetectioninremotesensingimages AT leyuanfang multigranularityselfattentionnetworkforfinegrainedshipdetectioninremotesensingimages AT xinyuji multigranularityselfattentionnetworkforfinegrainedshipdetectioninremotesensingimages |