Tri-training

Tri-Training is a semi-supervised learning framework in which three diverse models are iteratively trained on labeled data and subsequently leverage unlabeled data by mutually providing pseudo-labels to enhance each other’s generalization.

46

Publications

3.9K

Citations

160

Authors

68

Institutions

Publications per year

2017–2026

25

Authors

160

  1. JZ
    Jishuai Zhu

    China University of Mining and Technology, China

    2 publications · 42 citations

    2

    h-index

  2. KT
    Kun Tan

    China University of Mining and Technology, China

    2 publications · 42 citations

    2

    h-index

  3. YU
    Yoshitaka Ushiku

    The University of Tokyo, Japan

    2 publications · 462 citations

    2

    h-index

  4. KS
    Kuniaki Saito

    The University of Tokyo, Japan

    2 publications · 462 citations

    2

    h-index

  5. YY
    Yali Yuan

    University of Göttingen, Germany

    2 publications · 51 citations

    2

    h-index

1–5 of 160

Venues

  1. Knowledge-Based Systems

    2 publications · 30 citations

    2

    h-index

  2. Remote Sensing

    2 publications · 42 citations

    2

    h-index

  3. arXiv (Cornell University)

    Repository · 2 publications · 462 citations

    2

    h-index

  4. 1

    h-index

  5. Neurocomputing

    1 publications · 30 citations

    1

    h-index

1–5