Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 3.20 MB
Add to list
  1. Search results
  2. Know your self-supervised learning : ...

Know your self-supervised learning : a survey on image-based generative and discriminative training

Utku Özbulak, Hyun Jung Lee (UGent) , Beril Boga, Esla Timothy Anzaku (UGent) , Homin Park, Arnout Van Messem (UGent) , Wesley De Neve (UGent) and Joris Vankerschaver (UGent)
(2023) TRANSACTIONS ON MACHINE LEARNING RESEARCH.
Author
Organization
Abstract
Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a plateau is in sight. Meanwhile, the use of self-supervised learning (SSL) for the purpose of natural language processing (NLP) has seen tremendous successes during the past couple of years, with this new learning paradigm yielding powerful language models. Inspired by the excellent results obtained in the field of NLP, self-supervised methods that rely on clustering, contrastive learning, distillation, and information-maximization, which all fall under the banner of discriminative SSL, have experienced a swift uptake in the area of computer vision. Shortly afterwards, generative SSL frameworks that are mostly based on masked image modeling, complemented and surpassed the results obtained with discriminative SSL. Consequently, within a span of three years, over 100 unique general-purpose frameworks for generative and discriminative SSL, with a focus on imaging, were proposed. In this survey, we review a plethora of research efforts conducted on image-oriented SSL, providing a historic view and paying attention to best practices as well as useful software packages. While doing so, we discuss pretext tasks for image-based SSL, as well as techniques that are commonly used in image-based SSL. Lastly, to aid researchers who aim at contributing to image-focused SSL, we outline a number of promising research directions.

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.20 MB

Citation

Please use this url to cite or link to this publication:

MLA
Özbulak, Utku, et al. “Know Your Self-Supervised Learning : A Survey on Image-Based Generative and Discriminative Training.” TRANSACTIONS ON MACHINE LEARNING RESEARCH, no. 5, 2023.
APA
Özbulak, U., Lee, H. J., Boga, B., Anzaku, E. T., Park, H., Van Messem, A., … Vankerschaver, J. (2023). Know your self-supervised learning : a survey on image-based generative and discriminative training. TRANSACTIONS ON MACHINE LEARNING RESEARCH, (5).
Chicago author-date
Özbulak, Utku, Hyun Jung Lee, Beril Boga, Esla Timothy Anzaku, Homin Park, Arnout Van Messem, Wesley De Neve, and Joris Vankerschaver. 2023. “Know Your Self-Supervised Learning : A Survey on Image-Based Generative and Discriminative Training.” TRANSACTIONS ON MACHINE LEARNING RESEARCH, no. 5.
Chicago author-date (all authors)
Özbulak, Utku, Hyun Jung Lee, Beril Boga, Esla Timothy Anzaku, Homin Park, Arnout Van Messem, Wesley De Neve, and Joris Vankerschaver. 2023. “Know Your Self-Supervised Learning : A Survey on Image-Based Generative and Discriminative Training.” TRANSACTIONS ON MACHINE LEARNING RESEARCH (5).
Vancouver
1.
Özbulak U, Lee HJ, Boga B, Anzaku ET, Park H, Van Messem A, et al. Know your self-supervised learning : a survey on image-based generative and discriminative training. TRANSACTIONS ON MACHINE LEARNING RESEARCH. 2023;(5).
IEEE
[1]
U. Özbulak et al., “Know your self-supervised learning : a survey on image-based generative and discriminative training,” TRANSACTIONS ON MACHINE LEARNING RESEARCH, no. 5, 2023.
@article{01HM8DZ3EK2E22GB7D307HBH48,
  abstract     = {{Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a plateau is in sight. Meanwhile, the use of self-supervised learning (SSL) for the purpose of natural language processing (NLP) has seen tremendous successes during the past couple of years, with this new learning paradigm yielding powerful language models. Inspired by the excellent results obtained in the field of NLP, self-supervised methods that rely on clustering, contrastive learning, distillation, and information-maximization, which all fall under the banner of discriminative SSL, have experienced a swift uptake in the area of computer vision. Shortly afterwards, generative SSL frameworks that are mostly based on masked image modeling, complemented and surpassed the results obtained with discriminative SSL. Consequently, within a span of three years, over 100 unique general-purpose frameworks for generative and discriminative SSL, with a focus on imaging, were proposed. In this survey, we review a plethora of research efforts conducted on image-oriented SSL, providing a historic view and paying attention to best practices as well as useful software packages. While doing so, we discuss pretext tasks for image-based SSL, as well as techniques that are commonly used in image-based SSL. Lastly, to aid researchers who aim at contributing to image-focused SSL, we outline a number of promising research directions.}},
  author       = {{Özbulak, Utku and Lee, Hyun Jung and Boga, Beril and Anzaku, Esla Timothy and Park, Homin and Van Messem, Arnout and De Neve, Wesley and Vankerschaver, Joris}},
  issn         = {{2835-8856}},
  journal      = {{TRANSACTIONS ON MACHINE LEARNING RESEARCH}},
  language     = {{eng}},
  number       = {{5}},
  pages        = {{45}},
  title        = {{Know your self-supervised learning : a survey on image-based generative and discriminative training}},
  url          = {{https://openreview.net/pdf?id=Ma25S4ludQ}},
  year         = {{2023}},
}