Instance-incremental Learning

Instance-Incremental Learning is a paradigm within continual learning where the model incrementally learns from a sequence of instances without revisiting previous data, distinguished by the adaptation to new samples while preserving knowledge of past instances under the constraint of non-stationary data distribution shifts.

71

Publications

6.3K

Citations

221

Authors

112

Institutions

Publications per year

2017–2026

47

Authors

221

  1. MC
    M. Caccia

    European Organization for Nuclear Research, Switzerland

    3 publications · 101 citations

    3

    h-index

  2. PR
    Pau Rodríguez

    Universitat Autònoma de Barcelona, Spain

    3 publications · 101 citations

    3

    h-index

  3. IL
    Issam Laradji

    University of British Columbia, Canada

    3 publications · 101 citations

    3

    h-index

  4. DV
    David Vázquez

    Universitat Autònoma de Barcelona, Spain

    3 publications · 101 citations

    3

    h-index

  5. PZ
    Pietro Zanuttigh

    University of Padua, Italy

    2 publications · 103 citations

    2

    h-index

1–5 of 221

Venues

  1. Neurocomputing

    3 publications · 433 citations

    3

    h-index

  2. Pattern Recognition

    3 publications · 760 citations

    3

    h-index

  3. Information Sciences

    3 publications · 119 citations

    3

    h-index

  4. 2

    h-index

  5. arXiv (Cornell University)

    Repository · 2 publications · 41 citations

    2

    h-index

1–5