CANet: A Spatial Structure Constraint and Local Semantic Awareness Based Network for Weakly Supervised Building Extraction
发布时间：1905-07-17
点击次数：
- DOI码：
- 10.1109/tgrs.2025.3537099
- 所属单位：
- Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China
- 发表刊物：
- IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
- 项目来源：
- This work was supported in part by the National Key Research and Development Program of China under
- 关键字：
- Cams,Buildings,Semantics,Remote sensing,Feature extraction,Data mining,Accuracy,Semantic segmentation,Conditional random fields,Visualization,Building extraction,remote sensing,self-supervised learning (SSL),weakly supervised deep learning
- 摘要：
- Benefitting from the easy availability of image-level labels, weakly supervised semantic segmentation (WSSS) methods based on class activation maps (CAMs) have made significant progress in building extraction from remote sensing imagery. However, image-level labels lack precise spatial locations and boundary ranges of buildings, posing challenges in achieving comprehensive and structurally clear building extraction. Furthermore, due to the complex background interference and the diversity of building in high-resolution remote sensing imagery (HRRS), small and sparse buildings suffer from insuf
- 合写作者：
- Hou, Dongyang,Wang, Yu,Wang, Jinyang,Cai, Bowen
- 第一作者：
- Wang, Siyuan
- 论文类型：
- 期刊论文
- 通讯作者：
- Shao, Zhenfeng
- 文献类型：
- Article
- 卷号：
- 63
- ISSN号：
- 0196-2892
- 是否译文：
- 否
- 发表时间：
- 1905-07-17