ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

SITS-Former: A pre-trained spatio-spectral-temporal representation model for Sentinel-2 time series classification

Yuan, Yuan; Lin, Lei; Liu, Qingshan*; Hang, Renlong; Zhou, Zeng-Guang南京邮电大学; 中国科学院
International Journal of Applied Earth Observation and Geoinformation2022-2DOI: 10.1016/j.jag.2021.102651
50被引11阅读
引用收藏
分享

摘要

Sentinel-2 images provide a rich source of information for a variety of land cover, vegetation, and environmental monitoring applications due to their high spectral, spatial, and temporal resolutions. Recently, deep learning-based classification of Sentinel-2 time series becomes a popular solution to vegetation classification and land cover mapping, but it often demands a large number of manually annotated labels. Improving classification performance with limited labeled data is still a challenge in many real-world remote sensing applications. To address label scarcity, we present SITS-Former (SITS stands for Satellite Image Time Series and Former stands for Transformer), a pre-trained representation model for Sentinel-2 time series classification. SITS-Former adopts a Transformer encoder as the backbone and takes time series of image patches as input to learn spatio-spectral-temporal features. According to the principles of self-supervised learning, we pre-train SITS-Former on massive unlabeled Sentinel-2 time series via a missing-data imputation proxy task. Given an incomplete time series with some patches being masked randomly, the network is asked to regress the central pixels of these masked patches based on the residual ones. By doing so, the network can capture high-level spatial and temporal dependencies from the data to learn discriminative features. After pre-training, the network can adapt the learned features to a target classification task through fine-tuning. As far as we know, this is the first study that exploits self-supervised learning for patch-based representation learning and classification of SITS. We quantitatively evaluate the quality of the learned features by transferring them on two crop classification tasks, showing that SITS-Former outperforms state-of-the-art approaches and yields a significant improvement (2.64%similar to 3.30% in overall accuracy) over the purely supervised model. The proposed model provides an effective tool for SITS-related applications as it greatly reduces the burden of manual labeling. The source code will be released at htt ps://github.com/linlei1214/SITS-Former upon publication.

学科与关键词

关键词
Pre-trainingsatellite image time series (SITS)Self-supervised learningSentinel-2Transformer
相关
加载中…
  • Self-attention for raw optical Satellite Time Series Classification
    Russwurm, Marc*; Koerner, MarcoISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2020, 169: 421-435.被引 181
  • Remote Sensing Image Scene Classification with Self-Supervised Learning Based on Partially Unlabeled Datasets
    Chen, Xiliang; Zhu, Guobin*; Liu, MingqingRemote Sensing, 2022, 14(22): 5838.被引 10
  • Vision Transformers for Remote Sensing Image Classification
    Bazi, Yakoub*; Bashmal, Laila; Rahhal, Mohamad M. Al; Dayil, Reham Al; Ajlan, Naif AlRemote Sensing, 2021, 13(3): 516.被引 307
查看全部 →

发表信息

论文状态
公开发表
期刊
International Journal of Applied Earth Observation and Geoinformation
发表日期
2022-02
卷期
第 106 卷
页码
102651
DOI
10.1016/j.jag.2021.102651
期刊等级
1区
成果收录
SCIE
资助标注
National Natural Science Foun-dation of China [41901356, 61906096, 41701512]; Natural Science Foundation of Jiangsu Province [BK20180786]

作者

  • Y

    Yuan, Yuan (第一作者)

    nanjing univ informat sci & technol · nanjing univ posts & telecommun

  • L

    Lin, Lei

查看全部 5 位作者收起作者
  • L

    Liu, Qingshan (通讯)

    nanjing univ informat sci & technol

  • H

    Hang, Renlong

    nanjing univ informat sci & technol

  • Z

    Zhou, Zeng-Guang

    chinese acad sci

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417