Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images
Recently, semantic segmentation of water in synthetic aperture radar (SAR) images has attracted the attention of more and more scholars. However, existing methods usually require many accurate manually labeled pixel-level water annotations of SAR images, which leads to the problem that they are ofte...
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/10807843/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592961556185088 |
|---|---|
| author | Kai Wang Zhongle Ren Biao Hou Feng Sha Zhiyang Wang Weibin Li Licheng Jiao |
| author_facet | Kai Wang Zhongle Ren Biao Hou Feng Sha Zhiyang Wang Weibin Li Licheng Jiao |
| author_sort | Kai Wang |
| collection | DOAJ |
| description | Recently, semantic segmentation of water in synthetic aperture radar (SAR) images has attracted the attention of more and more scholars. However, existing methods usually require many accurate manually labeled pixel-level water annotations of SAR images, which leads to the problem that they are often time-consuming and costly. To mitigate this problem, we apply the weakly-supervised semantic segmentation (WSSS) and class activation maps (CAMs) to the semantic segmentation of water in SAR images. To address the issues of incomplete activation and false positives associated with applying existing CAM methods to semantic segmentation of water in SAR images, we propose a novel water-matching CAM to generate accurate CAMs of water. Water-matching CAM includes a multilevel water-backscatter guided module (MWGM) and a nonwater targets consistency module (NTCM). MWGM introduces a priori information on water backscatter for multilevel CAM generation, which can generate complete water CAMs using features at four different depths. NTCM further improves the performance of water CAM by subjecting nonwater targets to feature consistency constraints, which can effectively alleviate the issue of false positives. Then, we utilize the CAMs to generate pseudolabels to train the semantic segmentation of water models. Experiments on three datasets of SAR images taken by the GF-3 and Sentinel-1 satellite verify the validity of water-matching CAM. Our method achieves state-of-the-art performance compared to other CAM-based WSSS methods |
| format | Article |
| id | doaj-art-d16e7ba532aa483792cd37f5a4c27423 |
| institution | Kabale University |
| 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-d16e7ba532aa483792cd37f5a4c274232025-01-21T00:00:41ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183222323510.1109/JSTARS.2024.352036110807843Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR ImagesKai Wang0Zhongle Ren1https://orcid.org/0000-0002-5425-6437Biao Hou2https://orcid.org/0000-0002-1996-186XFeng Sha3Zhiyang Wang4Weibin Li5https://orcid.org/0000-0003-0047-8955Licheng Jiao6https://orcid.org/0000-0003-3354-9617Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, ChinaKey Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, ChinaKey Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, ChinaHigh Resolution Earth Observation System Shaanxi Data and Application Center, Xi'an, ChinaShaanxi Water Development Group Company Ltd., Xi'an, ChinaKey Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and The Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, ChinaKey Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, ChinaRecently, semantic segmentation of water in synthetic aperture radar (SAR) images has attracted the attention of more and more scholars. However, existing methods usually require many accurate manually labeled pixel-level water annotations of SAR images, which leads to the problem that they are often time-consuming and costly. To mitigate this problem, we apply the weakly-supervised semantic segmentation (WSSS) and class activation maps (CAMs) to the semantic segmentation of water in SAR images. To address the issues of incomplete activation and false positives associated with applying existing CAM methods to semantic segmentation of water in SAR images, we propose a novel water-matching CAM to generate accurate CAMs of water. Water-matching CAM includes a multilevel water-backscatter guided module (MWGM) and a nonwater targets consistency module (NTCM). MWGM introduces a priori information on water backscatter for multilevel CAM generation, which can generate complete water CAMs using features at four different depths. NTCM further improves the performance of water CAM by subjecting nonwater targets to feature consistency constraints, which can effectively alleviate the issue of false positives. Then, we utilize the CAMs to generate pseudolabels to train the semantic segmentation of water models. Experiments on three datasets of SAR images taken by the GF-3 and Sentinel-1 satellite verify the validity of water-matching CAM. Our method achieves state-of-the-art performance compared to other CAM-based WSSS methodshttps://ieeexplore.ieee.org/document/10807843/Class activation map (CAM)synthetic aperture radar (SAR)water semantic segmentationweakly-supervised learning |
| spellingShingle | Kai Wang Zhongle Ren Biao Hou Feng Sha Zhiyang Wang Weibin Li Licheng Jiao Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Class activation map (CAM) synthetic aperture radar (SAR) water semantic segmentation weakly-supervised learning |
| title | Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images |
| title_full | Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images |
| title_fullStr | Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images |
| title_full_unstemmed | Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images |
| title_short | Water-Matching CAM: A Novel Class Activation Map for Weakly-Supervised Semantic Segmentation of Water in SAR Images |
| title_sort | water matching cam a novel class activation map for weakly supervised semantic segmentation of water in sar images |
| topic | Class activation map (CAM) synthetic aperture radar (SAR) water semantic segmentation weakly-supervised learning |
| url | https://ieeexplore.ieee.org/document/10807843/ |
| work_keys_str_mv | AT kaiwang watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages AT zhongleren watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages AT biaohou watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages AT fengsha watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages AT zhiyangwang watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages AT weibinli watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages AT lichengjiao watermatchingcamanovelclassactivationmapforweaklysupervisedsemanticsegmentationofwaterinsarimages |