Few-shot Learning
Few-Shot Learning is a machine learning paradigm within meta-learning and transfer learning that enables models to generalize to new tasks from a minimal number of labeled examples, typically by leveraging prior knowledge acquired from related tasks.
3K
Publications
201.8K
Citations
9.1K
Authors
1.4K
Institutions
Publications per year
2017–2026
3K
3K
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard S. Zemel · arXiv (Cornell University) · 2017 · 5.2K citations · Full text
Language Models are Few-Shot Learners
T. B. Brown, Benjamin Mann, Nick Ryder et al. · arXiv (Cornell University) · 2020 · 3K citations · Full text
1–5 of 3K
9.1K
17
h-index
17
h-index
17
h-index
14
h-index
14
h-index
1–5 of 9.1K
1.4K

Chinese Academy of Sciences
Beijing, China
39 h-index
298 publications
13.4K citations
Tsinghua University
Beijing, China
37 h-index
217 publications
22K citations
Nanyang Technological University
Singapore, Singapore
37 h-index
144 publications
14.8K citations
Google (United States)
Mountain View, United States
36 h-index
173 publications
15.2K citations
University of Chinese Academy of Sciences
Beijing, China
36 h-index
262 publications
11.3K citations

Northwestern Polytechnical University
Xi'an, China
30 h-index
164 publications
12.7K citations

Zhejiang University
Hangzhou, China
29 h-index
144 publications
6.4K citations

Peking University
Beijing, China
28 h-index
100 publications
7.4K citations
1–8 of 1.4K
Repository · 553 publications · 47.2K citations
84
h-index
Conference · 89 publications · 5.3K citations
43
h-index
65 publications · 3.9K citations
36
h-index
Conference · 43 publications · 6.4K citations
32
h-index
TPAMI · 43 publications · 3.5K citations
30
h-index
1–5