SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing.
Interfered by external factors, the receptive field limits the traditional CNN multispectral remote sensing building change detection method. It is difficult to obtain detailed building changes entirely, and redundant information is reused in the encoding stage, which reduces the feature representat...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0306755 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206772082671616 |
|---|---|
| author | Shuai Pang Chaochao You Min Zhang Baojie Zhang Liyou Wang Xiaolong Shi Yu Sun |
| author_facet | Shuai Pang Chaochao You Min Zhang Baojie Zhang Liyou Wang Xiaolong Shi Yu Sun |
| author_sort | Shuai Pang |
| collection | DOAJ |
| description | Interfered by external factors, the receptive field limits the traditional CNN multispectral remote sensing building change detection method. It is difficult to obtain detailed building changes entirely, and redundant information is reused in the encoding stage, which reduces the feature representation and detection performance. To address these limitations, we design a Siamese network of shared attention aggregation to learn the detailed semantics of buildings in multispectral remote sensing images. On the one hand, a special attention embedding module is introduced into each subspace of the feature extractor to promote the interaction between multi-scale local features and enhance the representation of global features. On the other hand, a highly efficient channel and position multi-head attention module is added to the Siamese features to encode position details while sharing channel information. In addition, adopting a feature aggregation module with a residual strategy to fuse the features of different stages of the Siamese network is beneficial for detecting different scales and irregular object buildings. Finally, experimental results on LEVIR-CD and CDD datasets show that designed SAASNets have better accuracy and robustness. |
| format | Article |
| id | doaj-art-204a2fc1187d46b08d4364b7cc6cc480 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-204a2fc1187d46b08d4364b7cc6cc4802025-02-07T05:30:46ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e030675510.1371/journal.pone.0306755SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing.Shuai PangChaochao YouMin ZhangBaojie ZhangLiyou WangXiaolong ShiYu SunInterfered by external factors, the receptive field limits the traditional CNN multispectral remote sensing building change detection method. It is difficult to obtain detailed building changes entirely, and redundant information is reused in the encoding stage, which reduces the feature representation and detection performance. To address these limitations, we design a Siamese network of shared attention aggregation to learn the detailed semantics of buildings in multispectral remote sensing images. On the one hand, a special attention embedding module is introduced into each subspace of the feature extractor to promote the interaction between multi-scale local features and enhance the representation of global features. On the other hand, a highly efficient channel and position multi-head attention module is added to the Siamese features to encode position details while sharing channel information. In addition, adopting a feature aggregation module with a residual strategy to fuse the features of different stages of the Siamese network is beneficial for detecting different scales and irregular object buildings. Finally, experimental results on LEVIR-CD and CDD datasets show that designed SAASNets have better accuracy and robustness.https://doi.org/10.1371/journal.pone.0306755 |
| spellingShingle | Shuai Pang Chaochao You Min Zhang Baojie Zhang Liyou Wang Xiaolong Shi Yu Sun SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing. PLoS ONE |
| title | SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing. |
| title_full | SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing. |
| title_fullStr | SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing. |
| title_full_unstemmed | SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing. |
| title_short | SAASNets: Shared attention aggregation Siamese networks for building change detection in multispectral remote sensing. |
| title_sort | saasnets shared attention aggregation siamese networks for building change detection in multispectral remote sensing |
| url | https://doi.org/10.1371/journal.pone.0306755 |
| work_keys_str_mv | AT shuaipang saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing AT chaochaoyou saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing AT minzhang saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing AT baojiezhang saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing AT liyouwang saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing AT xiaolongshi saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing AT yusun saasnetssharedattentionaggregationsiamesenetworksforbuildingchangedetectioninmultispectralremotesensing |