SCAD: A Siamese Cross-Attention Discrimination Network for Bitemporal Building Change Detection

被引:6
|
作者
Xu, Chuan [1 ]
Ye, Zhaoyi [1 ]
Mei, Liye [1 ,2 ]
Shen, Sen [3 ]
Zhang, Qi [1 ]
Sui, Haigang [4 ]
Yang, Wei [5 ]
Sun, Shaohua [6 ]
机构
[1] Hubei Univ Technol, Sch Comp Sci, Wuhan 430068, Peoples R China
[2] Wuhan Univ, Inst Technol Sci, Wuhan 430072, Peoples R China
[3] Naval Engn Univ, Sch Weap Engn, Wuhan 430032, Peoples R China
[4] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430072, Peoples R China
[5] Wuchang Shouyi Univ, Sch Informat Sci & Engn, Wuhan 430064, Peoples R China
[6] Air Force Res Acad, Beijing 10085, Peoples R China
基金
中国国家自然科学基金;
关键词
building change detection; deep learning; Siamese cross-attention; feature fusion; differential context; COVER CHANGE DETECTION; IMAGE;
D O I
10.3390/rs14246213
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Building change detection (BCD) is crucial for urban construction and planning. The powerful discriminative ability of deep convolutions in deep learning-based BCD methods has considerably increased the accuracy and efficiency. However, dense and continuously distributed buildings contain a wide range of multi-scale features, which render current deep learning methods incapable of discriminating and incorporating multiple features effectively. In this work, we propose a Siamese cross-attention discrimination network (SCADNet) to identify complex information in bitemporal images and improve the change detection accuracy. Specifically, we first use the Siamese cross-attention (SCA) module to learn unchanged and changed feature information, combining multi-head cross-attention to improve the global validity of high-level semantic information. Second, we adapt a multi-scale feature fusion (MFF) module to integrate embedded tokens with context-rich channel transformer outputs. Then, upsampling is performed to fuse the extracted multi-scale information content to recover the original image information to the maximum extent. For information content with a large difference in contextual semantics, we perform filtering using a differential context discrimination (DCD) module, which can help the network to avoid pseudo-change occurrences. The experimental results show that the present SCADNet is able to achieve a significant change detection performance in terms of three public BCD datasets (LEVIR-CD, SYSU-CD, and WHU-CD). For these three datasets, we obtain F1 scores of 90.32%, 81.79%, and 88.62%, as well as OA values of 97.98%, 91.23%, and 98.88%, respectively.
引用
收藏
页数:21
相关论文
共 50 条
  • [41] Conjoint Cross-Attention Modeling and Joint Feature Calibrating for Remote Sensing Image Change Detection via a Triple-Double Network
    Liu, Fang
    An, Jiaqi
    Liu, Jia
    Yang, Jingxiang
    Tang, Xu
    Xiao, Liang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 16
  • [42] Multi-scale Cross Dual Attention Network for Building Change Detection in Remote Sensing Images
    Zhang J.
    Yan Z.
    Ma S.
    Journal of Geo-Information Science, 2023, 25 (12) : 2487 - 2500
  • [43] MAEANet: Multiscale Attention and Edge-Aware Siamese Network for Building Change Detection in High-Resolution Remote Sensing Images
    Yang, Bingjie
    Huang, Yuancheng
    Su, Xin
    Guo, Haonan
    REMOTE SENSING, 2022, 14 (19)
  • [44] Synchronous composition and semantic line detection based on cross-attention
    Hou, Qinggang
    Ke, Yongzhen
    Wang, Kai
    Qin, Fan
    Wang, Yaoting
    MULTIMEDIA SYSTEMS, 2024, 30 (03)
  • [45] Ship Detection in SAR Images via Cross-Attention Mechanism
    Lv, Yilong
    Li, Min
    CANADIAN JOURNAL OF REMOTE SENSING, 2022, 48 (06) : 764 - 778
  • [46] PRX-Change: Enhancing remote sensing change detection through progressive feature refinement and Cross-Attention interaction
    Tan, Haotian
    He, Linchao
    Du, Wenchao
    Liu, Hong
    Chen, Hu
    Zhang, Yi
    Yang, Hongyu
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2024, 132
  • [47] Deep Multiscale Siamese Network With Parallel Convolutional Structure and Self-Attention for Change Detection
    Guo, Qingle
    Zhang, Junping
    Zhu, Shengyu
    Zhong, Chongxiao
    Zhang, Ye
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [48] Multimodal Fusion Convolutional Neural Network With Cross-Attention Mechanism for Internal Defect Detection of Magnetic Tile
    Lu, Houhong
    Zhu, Yangyang
    Yin, Ming
    Yin, Guofu
    Xie, Luofeng
    IEEE ACCESS, 2022, 10 : 60876 - 60886
  • [49] CBSASNet: A Siamese Network Based on Channel Bias Split Attention for Remote Sensing Change Detection
    He, Naiwei
    Wang, Liejun
    Zheng, Panpan
    Zhang, Cui
    Li, Lele
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [50] Building Change Detection for Aerial Images Based on Attention Pyramid Network
    Tian Qinglin
    Qin Kai
    Chen Jun
    Li Yao
    Chen Xuejiao
    ACTA OPTICA SINICA, 2020, 40 (21)