Self-supervised Representation Learning
Self-Supervised Representation Learning is a machine learning framework that belongs to the class of representation learning methods, distinguished by its ability to generate supervisory signals from raw data without human-labeled annotations, thereby enabling the acquisition of meaningful feature representations through pretext tasks designed on the intrinsic structure of the input data.
1.2K
Publications
104.4K
Citations
4.4K
Authors
912
Institutions
Publications per year
2017–2026
1.1K
1.2K
A Simple Framework for Contrastive Learning of Visual Representations
Ting Chen, Simon Kornblith, Mohammad Norouzi et al. · arXiv (Cornell University) · 2020 · 7.3K citations · Full text
1–5 of 1.2K
4.4K
13
h-index
Korea Advanced Institute of Science and Technology, South Korea
12 publications · 2.1K citations
12
h-index
11
h-index
10
h-index
10
h-index
1–5 of 4.4K
912
Google (United States)
Mountain View, United States
30 h-index
184 publications
67.7K citations

Chinese Academy of Sciences
Beijing, China
28 h-index
126 publications
9.4K citations
Tsinghua University
Beijing, China
23 h-index
107 publications
23.6K citations
University of Science and Technology of China
Hefei, China
22 h-index
75 publications
5.1K citations
Meta (Israel)
Tel Aviv, Israel
22 h-index
67 publications
39.5K citations
University of Oxford
Oxford, United Kingdom
21 h-index
68 publications
5.4K citations
Carnegie Mellon University
Pittsburgh, United States
21 h-index
68 publications
5.5K citations
University of Chinese Academy of Sciences
Beijing, China
20 h-index
89 publications
6K citations
1–8 of 912
Repository · 265 publications · 28.1K citations
61
h-index
Conference · 33 publications · 7.2K citations
26
h-index
Conference · 34 publications · 2.8K citations
23
h-index
Conference · 34 publications · 2K citations
22
h-index
Conference · 16 publications · 544 citations
14
h-index
1–5