Few-shot Continual Learning

Few-Shot Continual Learning is a continual learning paradigm that enables models to rapidly adapt to new tasks from limited labeled examples while preserving knowledge of previously encountered tasks, thereby addressing the dual challenges of data scarcity and catastrophic forgetting in sequential learning scenarios.

30

Publications

949

Citations

154

Authors

55

Institutions

Publications per year

2017–2026

30

Authors

154

  1. MC
    M. Caccia

    European Organization for Nuclear Research, Switzerland

    3 publications · 68 citations

    3

    h-index

  2. DM
    Davide Maltoni

    University of Bologna, Italy

    2 publications · 51 citations

    2

    h-index

  3. LP
    Lorenzo Pellegrini

    University of Bologna, Italy

    2 publications · 51 citations

    2

    h-index

  4. MP
    Marc Pickett

    Google (United States), United States

    2 publications · 51 citations

    2

    h-index

  5. QS
    Qi She

    City University of Hong Kong, Hong Kong SAR China

    2 publications · 51 citations

    2

    h-index

1–5 of 154

Venues

  1. arXiv (Cornell University)

    Repository · 10 publications · 180 citations

    10

    h-index

  2. 2

    h-index

  3. 1

    h-index

  4. IEEE Transactions on Antennas and Propagation

    1 publications · 50 citations

    1

    h-index

  5. IEEE Access

    1 publications · 52 citations

    1

    h-index

1–5