Prototypical Learning

Prototypical Learning is a metric learning approach that learns class-specific prototypes in an embedding space, where each prototype serves as a representative summary of feature vectors for a given class, enabling classification through nearest-prototype distance comparison.

202

Publications

16.4K

Citations

619

Authors

258

Institutions

Publications per year

2017–2026

151

Authors

619

  1. RS
    Richard S. Zemel

    University of Toronto, Canada

    5 publications · 6.2K citations

    5

    h-index

  2. KS
    Kevin Swersky

    University of Toronto, Canada

    4 publications · 6.2K citations

    4

    h-index

  3. TP
    Tomas Pfister

    Google (United States), United States

    4 publications · 53 citations

    4

    h-index

  4. JS
    Jake Snell

    University of Toronto, Canada

    4 publications · 6.2K citations

    4

    h-index

  5. AM
    Ashutosh Modi

    Saarland University, Germany

    3 publications · 99 citations

    3

    h-index

1–5 of 619

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 7.4K citations

    17

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 377 citations

    6

    h-index

  3. 5

    h-index

  4. 5

    h-index

  5. Neurocomputing

    4 publications · 93 citations

    4

    h-index

1–5