MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images
With the development of deep learning (DL) in recent years, numerous remote sensing image change detection (CD) networks have emerged. However, existing DL-based CD networks still face two significant issues: 1) the lack of adequate supervision during the encoding process; and 2) the coupling of ove...
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/10843821/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857147616690176 |
|---|---|
| author | Daniyaer Sidekejiang Panpan Zheng Liejun Wang |
| author_facet | Daniyaer Sidekejiang Panpan Zheng Liejun Wang |
| author_sort | Daniyaer Sidekejiang |
| collection | DOAJ |
| description | With the development of deep learning (DL) in recent years, numerous remote sensing image change detection (CD) networks have emerged. However, existing DL-based CD networks still face two significant issues: 1) the lack of adequate supervision during the encoding process; and 2) the coupling of overall information with edge information. To overcome these challenges, we propose the Edge detection-guided (ED-guided) strategy and the Dual-flow strategy, integrating them into a novel Multilabel Dual-flow Network (MLDFNet). The ED-guided strategy supervises the encoding process with our self-generated edge labels, enabling feature extraction with reduced noise and more precise semantics. Concurrently, the Dual-flow strategy allows the network to process overall and edge information separately, reducing the interference between the two and enabling the network to observe both simultaneously. These strategies are effectively integrated through our proposed Dual-flow Convolution Block. Extensive experiments demonstrate that MLDFNet significantly outperforms existing state-of-the-art methods, achieving outstanding F1 scores of 91.72%, 97.84%, and 94.85% on the LEVIR-CD, CDD, and BCDD datasets, respectively. These results validate its superior performance and potential value in real-world remote sensing applications. |
| format | Article |
| id | doaj-art-99e8e29781a24179ae64440d3dfc208d |
| 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-99e8e29781a24179ae64440d3dfc208d2025-02-12T00:01:01ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184867488010.1109/JSTARS.2025.353014610843821MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing ImagesDaniyaer Sidekejiang0https://orcid.org/0009-0007-7466-1011Panpan Zheng1https://orcid.org/0009-0003-2934-6339Liejun Wang2https://orcid.org/0000-0003-0210-2273School of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaSchool of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaSchool of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaWith the development of deep learning (DL) in recent years, numerous remote sensing image change detection (CD) networks have emerged. However, existing DL-based CD networks still face two significant issues: 1) the lack of adequate supervision during the encoding process; and 2) the coupling of overall information with edge information. To overcome these challenges, we propose the Edge detection-guided (ED-guided) strategy and the Dual-flow strategy, integrating them into a novel Multilabel Dual-flow Network (MLDFNet). The ED-guided strategy supervises the encoding process with our self-generated edge labels, enabling feature extraction with reduced noise and more precise semantics. Concurrently, the Dual-flow strategy allows the network to process overall and edge information separately, reducing the interference between the two and enabling the network to observe both simultaneously. These strategies are effectively integrated through our proposed Dual-flow Convolution Block. Extensive experiments demonstrate that MLDFNet significantly outperforms existing state-of-the-art methods, achieving outstanding F1 scores of 91.72%, 97.84%, and 94.85% on the LEVIR-CD, CDD, and BCDD datasets, respectively. These results validate its superior performance and potential value in real-world remote sensing applications.https://ieeexplore.ieee.org/document/10843821/Change detection (CD)dual-flowedge detection (ED)supervision |
| spellingShingle | Daniyaer Sidekejiang Panpan Zheng Liejun Wang MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection (CD) dual-flow edge detection (ED) supervision |
| title | MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images |
| title_full | MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images |
| title_fullStr | MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images |
| title_full_unstemmed | MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images |
| title_short | MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images |
| title_sort | mldfnet a multilabel dual flow network for change detection in bitemporal remote sensing images |
| topic | Change detection (CD) dual-flow edge detection (ED) supervision |
| url | https://ieeexplore.ieee.org/document/10843821/ |
| work_keys_str_mv | AT daniyaersidekejiang mldfnetamultilabeldualflownetworkforchangedetectioninbitemporalremotesensingimages AT panpanzheng mldfnetamultilabeldualflownetworkforchangedetectioninbitemporalremotesensingimages AT liejunwang mldfnetamultilabeldualflownetworkforchangedetectioninbitemporalremotesensingimages |