ChangeViT: Unleashing plain vision transformers for change detection in remote sensing images
发布时间：2026-04-01
点击次数：
- DOI码：
- 10.1016/j.patcog.2025.112539
- 所属单位：
- Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan, Peoples R China
- 发表刊物：
- PATTERN RECOGNITION
- 项目来源：
- This work was supported by the Fundamental Research Funds for the Central Universities (2042024kf003
- 关键字：
- Change detection,Vision transformer,Remote sensing images
- 摘要：
- Change detection in remote sensing images is essential for monitoring environmental changes on Earth's surface. Although vision transformers (ViTs), particularly plain ViTs pre-trained on large-scale datasets and endowed with extensive knowledge and strong comprehension capabilities, have achieved remarkable success as backbones in numerous computer vision applications, they remain underutilized in change detection tasks. In this domain, convolutional neural networks (CNNs) continue to dominate due to their powerful feature extraction capabilities. In this paper, our study uncovers ViTs' uniqu
- 合写作者：
- Xiaohu, Haiyan,Cheng, Qimin,Huang, Zheng
- 第一作者：
- Zhu, Duowang
- 论文类型：
- 期刊论文
- 通讯作者：
- Shao, Zhenfeng
- 文献类型：
- Article
- 卷号：
- 172
- ISSN号：
- 0031-3203
- 是否译文：
- 否
- 发表时间：
- 2026-04-01