Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images
The study of remote sensing image object detection has excellent research value in environmental protection and public safety. However, the performance of the detectors is unsatisfactory due to the large variability of object size and complex background noise in remote sensing images. Therefore, it...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9858151/ |
| _version_ | 1828357015393533952 |
|---|---|
| author | Haotian Tan Yu Jiong Xueqiang Wan Junjie Wang |
| author_facet | Haotian Tan Yu Jiong Xueqiang Wan Junjie Wang |
| author_sort | Haotian Tan |
| collection | DOAJ |
| description | The study of remote sensing image object detection has excellent research value in environmental protection and public safety. However, the performance of the detectors is unsatisfactory due to the large variability of object size and complex background noise in remote sensing images. Therefore, it is essential to improve the detection performance of the detectors. Inspired by the idea of “divide and conquer”, we proposed a Multiple Receptive Field Attention (MRFA) to solve these problems and which is a plug-and-play attention method. First, we use the method of multiple receptive field feature map generation to convert the input feature map into four feature maps with different receptive fields. In this way, the small, medium, large, and immense objects in the input feature maps are “seen” in these feature maps, respectively. Then, we used the multiple attention map fusion method to focus objects of different sizes separately, which can effectively suppress noise in the background of remote sensing images. Experiments on remote sensing object detection datasets DIOR and HRRSD demonstrate that the performance of our method is better than other state-of-the-art attention modules. At the same time, the experiments on remote sensing image semantic segmentation dataset WHDLD and classification dataset AID prove the generalization and superiority of our method. |
| first_indexed | 2024-04-14T03:08:25Z |
| format | Article |
| id | doaj.art-8cee2965933e4ed782915c13b6572abb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-14T03:08:25Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8cee2965933e4ed782915c13b6572abb2022-12-22T02:15:40ZengIEEEIEEE Access2169-35362022-01-0110872668728110.1109/ACCESS.2022.31993689858151Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing ImagesHaotian Tan0https://orcid.org/0000-0001-8698-0115Yu Jiong1Xueqiang Wan2Junjie Wang3School of Information Science and Engineering, Xinjiang University, Urumqi, ChinaSchool of Information Science and Engineering, Xinjiang University, Urumqi, ChinaSchool of Software, Xinjiang University, Urumqi, ChinaSchool of Software, Xinjiang University, Urumqi, ChinaThe study of remote sensing image object detection has excellent research value in environmental protection and public safety. However, the performance of the detectors is unsatisfactory due to the large variability of object size and complex background noise in remote sensing images. Therefore, it is essential to improve the detection performance of the detectors. Inspired by the idea of “divide and conquer”, we proposed a Multiple Receptive Field Attention (MRFA) to solve these problems and which is a plug-and-play attention method. First, we use the method of multiple receptive field feature map generation to convert the input feature map into four feature maps with different receptive fields. In this way, the small, medium, large, and immense objects in the input feature maps are “seen” in these feature maps, respectively. Then, we used the multiple attention map fusion method to focus objects of different sizes separately, which can effectively suppress noise in the background of remote sensing images. Experiments on remote sensing object detection datasets DIOR and HRRSD demonstrate that the performance of our method is better than other state-of-the-art attention modules. At the same time, the experiments on remote sensing image semantic segmentation dataset WHDLD and classification dataset AID prove the generalization and superiority of our method.https://ieeexplore.ieee.org/document/9858151/Attention mechanismobject detectionremote sensing imagesimage processing |
| spellingShingle | Haotian Tan Yu Jiong Xueqiang Wan Junjie Wang Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images IEEE Access Attention mechanism object detection remote sensing images image processing |
| title | Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images |
| title_full | Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images |
| title_fullStr | Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images |
| title_full_unstemmed | Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images |
| title_short | Divide to Attend: A Multiple Receptive Field Attention Module for Object Detection in Remote Sensing Images |
| title_sort | divide to attend a multiple receptive field attention module for object detection in remote sensing images |
| topic | Attention mechanism object detection remote sensing images image processing |
| url | https://ieeexplore.ieee.org/document/9858151/ |
| work_keys_str_mv | AT haotiantan dividetoattendamultiplereceptivefieldattentionmoduleforobjectdetectioninremotesensingimages AT yujiong dividetoattendamultiplereceptivefieldattentionmoduleforobjectdetectioninremotesensingimages AT xueqiangwan dividetoattendamultiplereceptivefieldattentionmoduleforobjectdetectioninremotesensingimages AT junjiewang dividetoattendamultiplereceptivefieldattentionmoduleforobjectdetectioninremotesensingimages |