MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images
Recent deep-learning successes have led to a new wave of semantic segmentation in remote sensing (RS) applications. However, most approaches rarely distinguish the role of the body and edge of RS ground objects; thus, our understanding of these semantic parts has been frustrated by the lack of detai...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2023.2241435 |
| _version_ | 1797678432449986560 |
|---|---|
| author | Jiangfan Feng Panyu Chen Zhujun Gu Maimai Zeng Wei Zheng |
| author_facet | Jiangfan Feng Panyu Chen Zhujun Gu Maimai Zeng Wei Zheng |
| author_sort | Jiangfan Feng |
| collection | DOAJ |
| description | Recent deep-learning successes have led to a new wave of semantic segmentation in remote sensing (RS) applications. However, most approaches rarely distinguish the role of the body and edge of RS ground objects; thus, our understanding of these semantic parts has been frustrated by the lack of detailed geometry and appearance. Here we present a multiscale decoupled supervision network for RS semantic segmentation. Our proposed framework extends a densely supervised encoder-decoder network with a feature decoupling module that can decouple semantic features with different scales into distinct body and edge components. We further conduct multiscale supervision of the original and decoupled body and edge features to enhance inner consistency and spatial boundaries in remote sensing image (RSI) ground objects, enabling new segmentation designs and semantic components that can learn to perform multiscale geometry and appearance. Our results outperform the previous algorithm and are robust to different datasets. These results demonstrate that decoupled supervision is an effective solution to semantic segmentation tasks of RS images. |
| first_indexed | 2024-03-11T22:59:42Z |
| format | Article |
| id | doaj.art-812edae9c17e41438f1ed6c0c0e6598c |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T22:59:42Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-812edae9c17e41438f1ed6c0c0e6598c2023-09-21T15:09:03ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552023-12-011612844286110.1080/17538947.2023.22414352241435MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing imagesJiangfan Feng0Panyu Chen1Zhujun Gu2Maimai Zeng3Wei Zheng4Chongqing University of Posts and TelecommunicationsChongqing University of Posts and TelecommunicationsPearl River Water Resources CommissionPearl River Water Resources CommissionChongqing University of Posts and TelecommunicationsRecent deep-learning successes have led to a new wave of semantic segmentation in remote sensing (RS) applications. However, most approaches rarely distinguish the role of the body and edge of RS ground objects; thus, our understanding of these semantic parts has been frustrated by the lack of detailed geometry and appearance. Here we present a multiscale decoupled supervision network for RS semantic segmentation. Our proposed framework extends a densely supervised encoder-decoder network with a feature decoupling module that can decouple semantic features with different scales into distinct body and edge components. We further conduct multiscale supervision of the original and decoupled body and edge features to enhance inner consistency and spatial boundaries in remote sensing image (RSI) ground objects, enabling new segmentation designs and semantic components that can learn to perform multiscale geometry and appearance. Our results outperform the previous algorithm and are robust to different datasets. These results demonstrate that decoupled supervision is an effective solution to semantic segmentation tasks of RS images.http://dx.doi.org/10.1080/17538947.2023.2241435semantic segmentationremote sensing imagesedge supervisionmultiscale |
| spellingShingle | Jiangfan Feng Panyu Chen Zhujun Gu Maimai Zeng Wei Zheng MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images International Journal of Digital Earth semantic segmentation remote sensing images edge supervision multiscale |
| title | MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images |
| title_full | MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images |
| title_fullStr | MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images |
| title_full_unstemmed | MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images |
| title_short | MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images |
| title_sort | mdsnet a multiscale decoupled supervision network for semantic segmentation of remote sensing images |
| topic | semantic segmentation remote sensing images edge supervision multiscale |
| url | http://dx.doi.org/10.1080/17538947.2023.2241435 |
| work_keys_str_mv | AT jiangfanfeng mdsnetamultiscaledecoupledsupervisionnetworkforsemanticsegmentationofremotesensingimages AT panyuchen mdsnetamultiscaledecoupledsupervisionnetworkforsemanticsegmentationofremotesensingimages AT zhujungu mdsnetamultiscaledecoupledsupervisionnetworkforsemanticsegmentationofremotesensingimages AT maimaizeng mdsnetamultiscaledecoupledsupervisionnetworkforsemanticsegmentationofremotesensingimages AT weizheng mdsnetamultiscaledecoupledsupervisionnetworkforsemanticsegmentationofremotesensingimages |