Multi-Level Alignment Network for Cross-Domain Ship Detection
Ship detection is an important research topic in the field of remote sensing. Compared with optical detection methods, Synthetic Aperture Radar (SAR) ship detection can penetrate clouds to detect hidden ships in all-day and all-weather. Currently, the state-of-the-art methods exploit convolutional n...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/10/2389 |
| _version_ | 1797495972274634752 |
|---|---|
| author | Chujie Xu Xiangtao Zheng Xiaoqiang Lu |
| author_facet | Chujie Xu Xiangtao Zheng Xiaoqiang Lu |
| author_sort | Chujie Xu |
| collection | DOAJ |
| description | Ship detection is an important research topic in the field of remote sensing. Compared with optical detection methods, Synthetic Aperture Radar (SAR) ship detection can penetrate clouds to detect hidden ships in all-day and all-weather. Currently, the state-of-the-art methods exploit convolutional neural networks to train ship detectors, which require a considerable labeled dataset. However, it is difficult to label the SAR images because of expensive labor and well-trained experts. To address the above limitations, this paper explores a cross-domain ship detection task, which adapts the detector from labeled optical images to unlabeled SAR images. There is a significant visual difference between SAR images and optical images. To achieve cross-domain detection, the multi-level alignment network, which includes image-level, convolution-level, and instance-level, is proposed to reduce the large domain shift. First, image-level alignment exploits generative adversarial networks to generate SAR images from the optical images. Then, the generated SAR images and the real SAR images are used to train the detector. To further minimize domain distribution shift, the detector integrates convolution-level alignment and instance-level alignment. Convolution-level alignment trains the domain classifier on each activation of the convolutional features, which minimizes the domain distance to learn domain-invariant features. Instance-level alignment reduces domain distribution shift on the features extracted from the region proposals. The entire multi-level alignment network is trained end-to-end and its effectiveness is proved on multiple cross-domain ship detection datasets. |
| first_indexed | 2024-03-10T01:57:03Z |
| format | Article |
| id | doaj.art-9c08f7334c754b4b84f4502b58c5f72f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T01:57:03Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9c08f7334c754b4b84f4502b58c5f72f2023-11-23T12:55:24ZengMDPI AGRemote Sensing2072-42922022-05-011410238910.3390/rs14102389Multi-Level Alignment Network for Cross-Domain Ship DetectionChujie Xu0Xiangtao Zheng1Xiaoqiang Lu2Key Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaKey Laboratory of Spectral Imaging Technology CAS, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an 710119, ChinaShip detection is an important research topic in the field of remote sensing. Compared with optical detection methods, Synthetic Aperture Radar (SAR) ship detection can penetrate clouds to detect hidden ships in all-day and all-weather. Currently, the state-of-the-art methods exploit convolutional neural networks to train ship detectors, which require a considerable labeled dataset. However, it is difficult to label the SAR images because of expensive labor and well-trained experts. To address the above limitations, this paper explores a cross-domain ship detection task, which adapts the detector from labeled optical images to unlabeled SAR images. There is a significant visual difference between SAR images and optical images. To achieve cross-domain detection, the multi-level alignment network, which includes image-level, convolution-level, and instance-level, is proposed to reduce the large domain shift. First, image-level alignment exploits generative adversarial networks to generate SAR images from the optical images. Then, the generated SAR images and the real SAR images are used to train the detector. To further minimize domain distribution shift, the detector integrates convolution-level alignment and instance-level alignment. Convolution-level alignment trains the domain classifier on each activation of the convolutional features, which minimizes the domain distance to learn domain-invariant features. Instance-level alignment reduces domain distribution shift on the features extracted from the region proposals. The entire multi-level alignment network is trained end-to-end and its effectiveness is proved on multiple cross-domain ship detection datasets.https://www.mdpi.com/2072-4292/14/10/2389ship detectiondomain adaptationconvolutional neural networksynthetic aperture radar |
| spellingShingle | Chujie Xu Xiangtao Zheng Xiaoqiang Lu Multi-Level Alignment Network for Cross-Domain Ship Detection Remote Sensing ship detection domain adaptation convolutional neural network synthetic aperture radar |
| title | Multi-Level Alignment Network for Cross-Domain Ship Detection |
| title_full | Multi-Level Alignment Network for Cross-Domain Ship Detection |
| title_fullStr | Multi-Level Alignment Network for Cross-Domain Ship Detection |
| title_full_unstemmed | Multi-Level Alignment Network for Cross-Domain Ship Detection |
| title_short | Multi-Level Alignment Network for Cross-Domain Ship Detection |
| title_sort | multi level alignment network for cross domain ship detection |
| topic | ship detection domain adaptation convolutional neural network synthetic aperture radar |
| url | https://www.mdpi.com/2072-4292/14/10/2389 |
| work_keys_str_mv | AT chujiexu multilevelalignmentnetworkforcrossdomainshipdetection AT xiangtaozheng multilevelalignmentnetworkforcrossdomainshipdetection AT xiaoqianglu multilevelalignmentnetworkforcrossdomainshipdetection |