Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion
The limited number of samples in synthetic aperture radar (SAR) ship datasets hampers the advancement of target recognition performance using deep learning. Given the complex-valued nature of SAR data, incorporating spectrum information is beneficial for few-shot target recognition methods. However,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10966213/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850215395435216896 |
|---|---|
| author | Gui Gao WenXi Liu Xi Zhang |
| author_facet | Gui Gao WenXi Liu Xi Zhang |
| author_sort | Gui Gao |
| collection | DOAJ |
| description | The limited number of samples in synthetic aperture radar (SAR) ship datasets hampers the advancement of target recognition performance using deep learning. Given the complex-valued nature of SAR data, incorporating spectrum information is beneficial for few-shot target recognition methods. However, the SAR ship domain faces two significant issues: a scarcity of datasets that include spectrum information and a lack of target recognition networks specifically designed to leverage this spectrum information. In order to solve the above problems, first, a SpecGenGANwith generating pseudospectrum information is proposed to solve the problem of missing spectrum information. Second, a SpecAmpFusionNet is designed to fully exploit the deep features of spectrum and amplitude information. Finally, a few-shot target recognition method based on pseudospectrum information generation and fusion network is presented, allowing flexibility and integration with various popular recognition methods. Experimental results demonstrate that under 3way-10shots and 5way-10shots conditions, our method improves average accuracies by 12.04% and 10.83%, respectively, compared to methods using only amplitude information, validating the effectiveness of our approach in enhancing few-shot SAR ship recognition. |
| format | Article |
| id | doaj-art-b8367bc8b83c4fc592d7f8d643e6c3c4 |
| institution | OA Journals |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-b8367bc8b83c4fc592d7f8d643e6c3c42025-08-20T02:08:38ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118138251384310.1109/JSTARS.2025.356151610966213Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and FusionGui Gao0https://orcid.org/0000-0003-4596-5829WenXi Liu1https://orcid.org/0009-0001-9083-3203Xi Zhang2https://orcid.org/0000-0001-7907-6363Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu, ChinaLaboratory of Marine Physics and Remote Sensing, First Institute of Oceanography, Ministry of Natural Resources, Qingdao, ChinaThe limited number of samples in synthetic aperture radar (SAR) ship datasets hampers the advancement of target recognition performance using deep learning. Given the complex-valued nature of SAR data, incorporating spectrum information is beneficial for few-shot target recognition methods. However, the SAR ship domain faces two significant issues: a scarcity of datasets that include spectrum information and a lack of target recognition networks specifically designed to leverage this spectrum information. In order to solve the above problems, first, a SpecGenGANwith generating pseudospectrum information is proposed to solve the problem of missing spectrum information. Second, a SpecAmpFusionNet is designed to fully exploit the deep features of spectrum and amplitude information. Finally, a few-shot target recognition method based on pseudospectrum information generation and fusion network is presented, allowing flexibility and integration with various popular recognition methods. Experimental results demonstrate that under 3way-10shots and 5way-10shots conditions, our method improves average accuracies by 12.04% and 10.83%, respectively, compared to methods using only amplitude information, validating the effectiveness of our approach in enhancing few-shot SAR ship recognition.https://ieeexplore.ieee.org/document/10966213/Domain transfership recognitionspectrum informationsynthetic aperture radar (SAR) |
| spellingShingle | Gui Gao WenXi Liu Xi Zhang Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Domain transfer ship recognition spectrum information synthetic aperture radar (SAR) |
| title | Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion |
| title_full | Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion |
| title_fullStr | Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion |
| title_full_unstemmed | Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion |
| title_short | Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion |
| title_sort | enhancing few shot sar ship recognition pseudospectrum information generation and fusion |
| topic | Domain transfer ship recognition spectrum information synthetic aperture radar (SAR) |
| url | https://ieeexplore.ieee.org/document/10966213/ |
| work_keys_str_mv | AT guigao enhancingfewshotsarshiprecognitionpseudospectruminformationgenerationandfusion AT wenxiliu enhancingfewshotsarshiprecognitionpseudospectruminformationgenerationandfusion AT xizhang enhancingfewshotsarshiprecognitionpseudospectruminformationgenerationandfusion |