Few-shot Classification
Few-Shot Classification is a meta-learning task that involves training a model to classify novel categories from a limited number of labeled examples per class, typically ranging from one to a few dozen instances.
816
Publications
67.1K
Citations
2.8K
Authors
598
Institutions
Publications per year
2017–2026
814
Parents
816
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard S. Zemel · arXiv (Cornell University) · 2017 · 5.2K citations · Full text
Meta-Transfer Learning for Few-Shot Learning
Qianru Sun, Yaoyao Liu, Tat‐Seng Chua et al. · 2019 · 1.3K citations
Dynamic Few-Shot Visual Learning Without Forgetting
Spyros Gidaris, Nikos Komodakis · 2018 · 1.1K citations
1–5 of 816
2.8K
10
h-index
8
h-index
8
h-index
8
h-index
8
h-index
1–5 of 2.8K
598

Chinese Academy of Sciences
Beijing, China
27 h-index
116 publications
6K citations
University of Chinese Academy of Sciences
Beijing, China
23 h-index
90 publications
5.2K citations

Northwestern Polytechnical University
Xi'an, China
20 h-index
97 publications
6.7K citations
Google (United States)
Mountain View, United States
17 h-index
45 publications
4.4K citations
Nanjing University
Nanjing, China
17 h-index
51 publications
7K citations

Xidian University
Xi'an, China
16 h-index
73 publications
3.6K citations

Peking University
Beijing, China
16 h-index
38 publications
3.1K citations
Tsinghua University
Beijing, China
16 h-index
48 publications
6K citations
1–8 of 598
Repository · 162 publications · 22K citations
56
h-index
48 publications · 2.8K citations
31
h-index
Conference · 37 publications · 2.2K citations
24
h-index
TPAMI · 16 publications · 874 citations
16
h-index
18 publications · 704 citations
16
h-index
1–5