Self-supervised Learning For Geospatial Data

Self-Supervised Learning for Geospatial Data is a machine learning paradigm that leverages the inherent spatial, temporal, and spectral structures of unlabeled geospatial observations to generate pretext tasks for representation learning, thereby enabling the acquisition of generalizable feature embeddings without reliance on manually annotated training data.

18

Publications

879

Citations

101

Authors

38

Institutions

Publications per year

2017–2026

16

Authors

101

  1. LC
    Linsong Chu

    University of Alabama in Huntsville, United States

    2 publications · 110 citations

    2

    h-index

  2. BZ
    Bianca Zadrozny

    Universidade Federal Fluminense, Brazil

    2 publications · 110 citations

    2

    h-index

  3. JC
    Jocelyn Chanussot

    Institut polytechnique de Grenoble, France

    2 publications · 97 citations

    2

    h-index

  4. SR
    Sujit Roy

    University of Ulster, United Kingdom

    2 publications · 110 citations

    2

    h-index

  5. RR
    Rahul Ramachandran

    University of Alabama in Huntsville, United States

    2 publications · 110 citations

    2

    h-index

1–5 of 101

Venues

  1. arXiv (Cornell University)

    Repository · 5 publications · 149 citations

    5

    h-index

  2. IEEE Geoscience and Remote Sensing Magazine

    GRSM · 1 publications · 110 citations

    1

    h-index

  3. 1

    h-index

  4. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 1 publications · 102 citations

    1

    h-index

  5. 1

    h-index

1–5