Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery
In recent years, numerous change detection methodologies have been proposed, with a predominant focus on binary change detection. Furthermore, there exists a paucity of research addressing semantic change detection in scenarios where solely binary change labels are available. This article introduces...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10378854/ |
| _version_ | 1797351706085818368 |
|---|---|
| author | Dawei Wen Xin Huang Qiquan Yang Jianqin Tang |
| author_facet | Dawei Wen Xin Huang Qiquan Yang Jianqin Tang |
| author_sort | Dawei Wen |
| collection | DOAJ |
| description | In recent years, numerous change detection methodologies have been proposed, with a predominant focus on binary change detection. Furthermore, there exists a paucity of research addressing semantic change detection in scenarios where solely binary change labels are available. This article introduces a multitask network for semantic change detection. First, 3-D ResUnet model is employed to generate initial multitemporal land cover results through postclassification comparison. Subsequently, the multitask network, encompassing two subtasks—binary change detection and multitemporal semantic segmentation—is proposed. Specifically, the shared branch of the network employs 3-D residual blocks to extract joint spectral-spatial features. In the subsequent task-specific branch, a 3-D GAN is incorporated for the binary change detection task to enhance the discrimination ability of latent high-level features for changes. Novel adaptive self-paced learning and certainty-weighted focal loss are proposed for multitemporal semantic segmentation to mitigate adverse effects from noisy semantic labels by considering sample complexity and reliability in the network optimization process. Experiments conducted on the Orbita Hyperspectral dataset in the Xiong'an New Area demonstrate the superior performance of the proposed method, achieving 99.28% and 76.60% for overall accuracy and kappa, respectively. This outperformance is notable when compared to other methods, such as Str4 and Bi-SRNet, showing an increase of 39.82% and 54.17% for kappa. Moreover, comparative experiments on SECOND further confirm the advantage of the proposed method, achieving 54.62% for kappa and outperforming other comparative methods, such as Bi-SRNet (47.61%). |
| first_indexed | 2024-03-08T13:04:24Z |
| format | Article |
| id | doaj.art-9370a3c7547648b19b71bfc17ea68667 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-08T13:04:24Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-9370a3c7547648b19b71bfc17ea686672024-01-19T00:00:11ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01172777278810.1109/JSTARS.2023.334857210378854Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing ImageryDawei Wen0https://orcid.org/0000-0001-9290-1276Xin Huang1https://orcid.org/0000-0002-5625-0338Qiquan Yang2https://orcid.org/0000-0003-1152-5999Jianqin Tang3https://orcid.org/0009-0001-2093-3305School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, The Hubei Luojia Laboratory, Wuhan University, Wuhan, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaSchool of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, ChinaIn recent years, numerous change detection methodologies have been proposed, with a predominant focus on binary change detection. Furthermore, there exists a paucity of research addressing semantic change detection in scenarios where solely binary change labels are available. This article introduces a multitask network for semantic change detection. First, 3-D ResUnet model is employed to generate initial multitemporal land cover results through postclassification comparison. Subsequently, the multitask network, encompassing two subtasks—binary change detection and multitemporal semantic segmentation—is proposed. Specifically, the shared branch of the network employs 3-D residual blocks to extract joint spectral-spatial features. In the subsequent task-specific branch, a 3-D GAN is incorporated for the binary change detection task to enhance the discrimination ability of latent high-level features for changes. Novel adaptive self-paced learning and certainty-weighted focal loss are proposed for multitemporal semantic segmentation to mitigate adverse effects from noisy semantic labels by considering sample complexity and reliability in the network optimization process. Experiments conducted on the Orbita Hyperspectral dataset in the Xiong'an New Area demonstrate the superior performance of the proposed method, achieving 99.28% and 76.60% for overall accuracy and kappa, respectively. This outperformance is notable when compared to other methods, such as Str4 and Bi-SRNet, showing an increase of 39.82% and 54.17% for kappa. Moreover, comparative experiments on SECOND further confirm the advantage of the proposed method, achieving 54.62% for kappa and outperforming other comparative methods, such as Bi-SRNet (47.61%).https://ieeexplore.ieee.org/document/10378854/Change detectionhyperspectral remote sensingmultitask learningpseudolabelsemantic change detection |
| spellingShingle | Dawei Wen Xin Huang Qiquan Yang Jianqin Tang Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection hyperspectral remote sensing multitask learning pseudolabel semantic change detection |
| title | Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery |
| title_full | Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery |
| title_fullStr | Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery |
| title_full_unstemmed | Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery |
| title_short | Adaptive Self-Paced Collaborative and 3-D Adversarial Multitask Network for Semantic Change Detection Using Zhuhai-1 Orbita Hyperspectral Remote Sensing Imagery |
| title_sort | adaptive self paced collaborative and 3 d adversarial multitask network for semantic change detection using zhuhai 1 orbita hyperspectral remote sensing imagery |
| topic | Change detection hyperspectral remote sensing multitask learning pseudolabel semantic change detection |
| url | https://ieeexplore.ieee.org/document/10378854/ |
| work_keys_str_mv | AT daweiwen adaptiveselfpacedcollaborativeand3dadversarialmultitasknetworkforsemanticchangedetectionusingzhuhai1orbitahyperspectralremotesensingimagery AT xinhuang adaptiveselfpacedcollaborativeand3dadversarialmultitasknetworkforsemanticchangedetectionusingzhuhai1orbitahyperspectralremotesensingimagery AT qiquanyang adaptiveselfpacedcollaborativeand3dadversarialmultitasknetworkforsemanticchangedetectionusingzhuhai1orbitahyperspectralremotesensingimagery AT jianqintang adaptiveselfpacedcollaborativeand3dadversarialmultitasknetworkforsemanticchangedetectionusingzhuhai1orbitahyperspectralremotesensingimagery |