Vision Self-supervised Learning
Vision Self-Supervised Learning is a machine learning paradigm that belongs to the broader category of self-supervised learning, distinguished by its focus on learning rich visual representations from unlabeled image or video data through automatically generated supervision signals derived from the intrinsic structure of visual inputs.
296
Publications
30.8K
Citations
1.1K
Authors
286
Institutions
Publications per year
2017–2026
280
Parents
296
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Sanghyun Woo, Shoubhik Debnath, Ronghang Hu et al. · 2023 · 1.3K citations
DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab, Timothée Darcet, Théo Moutakanni et al. · arXiv (Cornell University) · 2023 · 1K citations · Full text
1–5 of 296
1.1K
10
h-index
8
h-index
8
h-index
6
h-index
Korea Advanced Institute of Science and Technology, South Korea
5 publications · 1.5K citations
6
h-index
1–5 of 1.1K
286
Carnegie Mellon University
Pittsburgh, United States
9 h-index
23 publications
1.1K citations
Google (United States)
Mountain View, United States
8 h-index
13 publications
2.7K citations
University of Oxford
Oxford, United Kingdom
8 h-index
19 publications
1.6K citations

Peking University
Beijing, China
7 h-index
23 publications
1.4K citations
Meta (Israel)
Tel Aviv, Israel
7 h-index
26 publications
38.4K citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
6 h-index
16 publications
1.3K citations
Technical University of Munich
Munich, Germany
6 h-index
17 publications
775 citations

Shanghai Jiao Tong University
Shanghai, China
5 h-index
9 publications
372 citations
1–8 of 286
Repository · 95 publications · 7.1K citations
37
h-index
Conference · 10 publications · 7.1K citations
10
h-index
7 publications · 453 citations
9
h-index
Conference · 7 publications · 1.3K citations
7
h-index
Conference · 5 publications · 162 citations
6
h-index
1–5