Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Coding

被引:66
|
作者
Stojnic, Vladan [1 ]
Risojevic, Vladimir [1 ]
机构
[1] Univ Banja Luka, Fac Elect Engn, Banja Luka, Bosnia & Herceg
关键词
BENCHMARK; DATASET;
D O I
10.1109/CVPRW53098.2021.00129
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its applicability is especially interesting in specific areas, like remote sensing and medicine, where it is hard to obtain huge amounts of labeled data. In this work, we conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification. We analyze the influence of the number and domain of images used for self-supervised pre-training on the performance on downstream tasks. We show that, for the downstream task of remote sensing image classification, using self-supervised pre-training on remote sensing images can give better results than using supervised pre-training on images of natural scenes. Besides, we also show that self-supervised pre-training can be easily extended to multispectral images producing even better results on our downstream tasks.
引用
收藏
页码:1182 / 1191
页数:10
相关论文
共 50 条
  • [1] Contrastive Self-Supervised Learning With Smoothed Representation for Remote Sensing
    Jung, Heechul
    Oh, Yoonju
    Jeong, Seongho
    Lee, Chaehyeon
    Jeon, Taegyun
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [2] Multicue Contrastive Self-Supervised Learning for Change Detection in Remote Sensing
    Yang, Meijuan
    Jiao, Licheng
    Liu, Fang
    Hou, Biao
    Yang, Shuyuan
    Zhang, Yake
    Wang, Jianlong
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61 : 1 - 14
  • [3] Scene Text Recognition with Self-supervised Contrastive Predictive Coding
    Jiang, Xinzhe
    Zhang, Jianshu
    Du, Jun
    Zhang, Zhenrong
    Wu, Jiajia
    [J]. 2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 1514 - 1521
  • [4] MANIFOLD AUGMENTATION BASED SELF-SUPERVISED CONTRASTIVE LEARNING FOR FEW-SHOT REMOTE SENSING SCENE CLASSIFICATION
    Sheng, Yunrui
    Xiao, Liang
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 2239 - 2242
  • [5] Self-Supervised Learning in Remote Sensing
    Wang, Yi
    Albrecht, Conrad M.
    Ait Ali Braham, Nassim
    Mou, Lichao
    Zhu, Xiao Xiang
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2022, 10 (04) : 213 - 247
  • [6] Self-Supervised Change Detection in Multiview Remote Sensing Images
    Chen, Yuxing
    Bruzzone, Lorenzo
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [7] CONTRASTIVE SEPARATIVE CODING FOR SELF-SUPERVISED REPRESENTATION LEARNING
    Wang, Jun
    Lam, Max W. Y.
    Su, Dan
    Yu, Dong
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 3865 - 3869
  • [8] Shot Contrastive Self-Supervised Learning for Scene Boundary Detection
    Chen, Shixing
    Nie, Xiaohan
    Fan, David
    Zhang, Dongqing
    Bhat, Vimal
    Hamid, Raffay
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 9791 - 9800
  • [9] Multi-Source Remote Sensing Pretraining Based on Contrastive Self-Supervised Learning
    Liu, Chenfang
    Sun, Hao
    Xu, Yanjie
    Kuang, Gangyao
    [J]. REMOTE SENSING, 2022, 14 (18)
  • [10] Self-Supervised Visual Representations Learning by Contrastive Mask Prediction
    Zhao, Yucheng
    Wang, Guangting
    Luo, Chong
    Zeng, Wenjun
    Zha, Zheng-Jun
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 10140 - 10149