SemiPSENet: A Novel Semi-Supervised Change Detection Network for Remote Sensing Images

被引:0
|
作者
Hu, Lei [1 ]
Li, Supeng [1 ]
Ruan, Jiachen [1 ]
Gao, Feng [2 ]
机构
[1] Jiangxi Normal Univ, Sch Comp & Informat Engn, Nanchang 330022, Peoples R China
[2] Ocean Univ China, Sch Comp Sci & Technol, Qingdao 266100, Peoples R China
基金
中国国家自然科学基金;
关键词
Feature extraction; Remote sensing; Supervised learning; Semantics; Training; Task analysis; Semisupervised learning; Change detection; consistent regularization; GELU_PSP module; remote sensing image; semi-supervised learning;
D O I
10.1109/TGRS.2024.3434427
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Currently, high-precision fully supervised methods are mainly used in the change detection tasks of high-resolution remote sensing images, which require a large amount of labeled data. However, labeling huge amounts of sample data is costly. In order to solve this limitation, a SemiPSENet based on consistent regularization is proposed. SemiPSENet consists of two parts: a supervised phase and an unsupervised phase, which is trained jointly with a small amount of labeled data and a large amount of unlabeled data. In the supervision phase, to generate a multiscale feature map that can fuse more context information, a GELU_PSP module is designed, which can greatly reduce the loss of semantic information. The squeeze-and-excitation (SE) attention module is added after GELU_PSP module, which can highlight important changing features and neglect irrelevant information based on the importance of each feature channel. In the unsupervised phase, to process the unlabeled data, the consistency regularization method is adopted, which can make the predictive change map have the consistency ability under different random perturbations, so that the semantic information can fully be used in the unlabeled image. Experiments on two public datasets LEVIR-CD and WHU show that the proposed SemiPSENet can achieve excellent detection results by relying on the training of a small amount of labeled data and a large amount of unlabeled data. Notably, our network performs better than other SOTA methods when using the same amount of labeled data.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Change detection of remote sensing images with semi-supervised multilayer perceptron
    Department of Computer Science and Engineering, Jadavpur University, Kolkata 700 032, India
    不详
    不详
    [J]. Fundam Inf, 2008, 3-4 (429-442):
  • [2] Change detection of remote sensing images with semi-supervised multilayer perceptron
    Patra, Swarnajyoti
    Ghosh, Susmita
    Ghosh, Ashish
    [J]. FUNDAMENTA INFORMATICAE, 2008, 84 (3-4) : 429 - 442
  • [3] Reliable Contrastive Learning for Semi-Supervised Change Detection in Remote Sensing Images
    Wang, Jia-Xin
    Li, Teng
    Chen, Si-Bao
    Tang, Jin
    Luo, Bin
    Wilson, Richard C.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [4] Prototype Discriminative Learning for Semi-Supervised Change Detection in Remote Sensing Images
    You, Zhi-Hui
    Chen, Si-Bao
    Wang, Jia-Xin
    Ding, Chris H. Q.
    Tang, Jin
    Luo, Bin
    [J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62
  • [5] Semi-supervised Change Detection Technique on Remote Sensing Images Using Posterior Probabilities
    Raha, Srija
    Saha, Kasturi
    Sil, Shreya
    Halder, Amiya
    [J]. COMPUTATIONAL INTELLIGENCE IN PATTERN RECOGNITION, CIPR 2020, 2020, 1120 : 269 - 276
  • [6] Consistency-guided lightweight network for semi-supervised binary change detection of buildings in remote sensing images
    Ding, Qing
    Shao, Zhenfeng
    Huang, Xiao
    Feng, Xiaoxiao
    Altan, Orhan
    Hu, Bin
    [J]. GISCIENCE & REMOTE SENSING, 2023, 60 (01)
  • [7] Robust Instance-Based Semi-Supervised Learning Change Detection for Remote Sensing Images
    Zuo, Yi
    Li, Lingling
    Liu, Xu
    Gao, Zihan
    Jiao, Licheng
    Liu, Fang
    Yang, Shuyuan
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 (1-15):
  • [8] Learning Remote Sensing Aleatoric Uncertainty for Semi-Supervised Change Detection
    Shen, Jinhao
    Zhang, Cong
    Zhang, Mingwei
    Li, Qiang
    Wang, Qi
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [9] Wavelet Siamese Network With Semi-Supervised Domain Adaptation for Remote Sensing Image Change Detection
    Xiong, Fengchao
    Li, Tianhan
    Yang, Yi
    Zhou, Jun
    Lu, Jianfeng
    Qian, Yuntao
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [10] Semi-Supervised Semantic Segmentation of Remote Sensing Images With Iterative Contrastive Network
    Wang, Jia-Xin
    Chen, Si-Bao
    Ding, Chris H. Q.
    Tang, Jin
    Luo, Bin
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19