Instance-based Transfer

Instance-Based Transfer is a transfer learning approach that belongs to the category of methods leveraging source domain instances directly in the target domain learning process, distinguished by reusing or reweighting actual data instances from the source domain rather than transferring model parameters or feature representations.

62

Publications

2.9K

Citations

249

Authors

115

Institutions

Publications per year

2017–2026

46

Variants

Instance-based Transfer Learning

Authors

249

  1. MZ
    Mengjie Zhang

    Victoria University of Wellington, New Zealand

    2 publications · 31 citations

    2

    h-index

  2. BX
    Bing Xue

    Victoria University of Wellington, New Zealand

    2 publications · 31 citations

    2

    h-index

  3. CL
    Chao Lu

    Beijing Institute of Technology, China

    2 publications · 42 citations

    2

    h-index

  4. MD
    Marie desJardins

    University of Maryland, Baltimore County, United States

    2 publications · 101 citations

    2

    h-index

  5. EE
    Eric Eaton

    University of Pennsylvania, United States

    2 publications · 101 citations

    2

    h-index

1–5 of 249

Venues

  1. IEEE Access

    2 publications · 59 citations

    2

    h-index

  2. 2

    h-index

  3. Pattern Recognition Letters

    2 publications · 95 citations

    2

    h-index

  4. Quarterly Journal of Experimental Psychology

    QJEP · 1 publications · 23 citations

    1

    h-index

  5. Journal Of Big Data

    1 publications · 18 citations

    1

    h-index

1–5