Back to Search Start Over

Connecting the Dots in Self-Supervised Learning: A Brief Survey for Beginners.

Authors :
Fang, Peng-Fei
Li, Xian
Yan, Yang
Zhang, Shuai
Kang, Qi-Yue
Li, Xiao-Fei
Lan, Zhen-Zhong
Source :
Journal of Computer Science & Technology (10009000); Jun2022, Vol. 37 Issue 3, p507-526, 20p
Publication Year :
2022

Abstract

The artificial intelligence (AI) community has recently made tremendous progress in developing self-supervised learning (SSL) algorithms that can learn high-quality data representations from massive amounts of unlabeled data. These methods brought great results even to the fields outside of AI. Due to the joint efforts of researchers in various areas, new SSL methods come out daily. However, such a sheer number of publications make it difficult for beginners to see clearly how the subject progresses. This survey bridges this gap by carefully selecting a small portion of papers that we believe are milestones or essential work. We see these researches as the "dots" of SSL and connect them through how they evolve. Hopefully, by viewing the connections of these dots, readers will have a high-level picture of the development of SSL across multiple disciplines including natural language processing, computer vision, graph learning, audio processing, and protein learning. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
10009000
Volume :
37
Issue :
3
Database :
Complementary Index
Journal :
Journal of Computer Science & Technology (10009000)
Publication Type :
Academic Journal
Accession number :
157529656
Full Text :
https://doi.org/10.1007/s11390-022-2158-x