Concepedia

Self-supervised Fine-tuning

Self-Supervised Fine-Tuning is a model adaptation strategy that belongs to the class of self-supervised learning methods, distinguished by its refinement of a pre-trained representation through task-specific supervised learning while retaining the unsupervised pre-training paradigm as its foundational inductive bias.

90

Publications

6.9K

Citations

444

Authors

135

Institutions

Publications per year

2017–2026

89

Parents

Publications

90

Pre-trained models: Past, present and future

Xu Han, Zhengyan Zhang, Ning Ding et al. · AI Open · 2021 · 938 citations · Full text

, , +15

Big Self-Supervised Models Advance Medical Image Classification

Shekoofeh Azizi, Basil Mustafa, Fiona Ryan et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 609 citations

, , +17

Colorization as a Proxy Task for Visual Understanding

Gustav Larsson, Michael Maire, Gregory Shakhnarovich · 2017 · 485 citations

, , +16

Big Self-Supervised Models are Strong Semi-Supervised Learners

Ting Chen, Simon Kornblith, Kevin Swersky et al. · arXiv (Cornell University) · 2020 · 476 citations · Full text

, , +16

Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

Iulia Turc, Ming‐Wei Chang, Kenton Lee et al. · arXiv (Cornell University) · 2019 · 429 citations · Full text

, , +14

1–5 of 90

Authors

444

  1. HL
    Hung-yi Lee

    National Taiwan University, Taiwan

    4 publications · 386 citations

    4

    h-index

  2. AB
    Alexei Baevski

    Meta (Israel), Israel

    3 publications · 218 citations

    3

    h-index

  3. JW
    Ji-Rong Wen

    Renmin University of China, China

    3 publications · 997 citations

    3

    h-index

  4. XQ
    Xipeng Qiu

    Fudan University, China

    3 publications · 1K citations

    3

    h-index

  5. MA
    Michael Auli

    Meta (Israel), Israel

    2 publications · 118 citations

    2

    h-index

1–5 of 444

Institutions

135

  1. Tencent (China)

    Shenzhen, China

    4 h-index

    12 publications

    547 citations

  2. Google (United States)

    Mountain View, United States

    4 h-index

    29 publications

    10.3K citations

  3. National Taiwan University

    Taipei, Taiwan

    4 h-index

    11 publications

    844 citations

  4. University of Chinese Academy of Sciences

    Beijing, China

    3 h-index

    3 publications

    66 citations

  5. Renmin University of China

    Beijing, China

    3 h-index

    17 publications

    6.8K citations

  6. Meta (Israel)

    Tel Aviv, Israel

    3 h-index

    14 publications

    498 citations

  7. Chinese Academy of Sciences

    Beijing, China

    3 h-index

    10 publications

    209 citations

  8. Fudan University

    Shanghai, China

    3 h-index

    5 publications

    1.1K citations

1–8 of 135

Venues

  1. arXiv (Cornell University)

    Repository · 18 publications · 1.5K citations

    14

    h-index

  2. Interspeech 2022

    Conference · 3 publications · 95 citations

    3

    h-index

  3. 3

    h-index

  4. 3

    h-index

  5. Remote Sensing

    3 publications · 99 citations

    3

    h-index

1–5