Science Explorer Back to mapMap
Discussion
Topic · Artificial Intelligence

Domain Adaptation and Few-Shot Learning

Domain Adaptation and Few-Shot Learning is a research topic within Artificial Intelligence. Science Explorer counts 23k research works in it since 1951. 9.7% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the advances in transfer learning and domain adaptation, including topics such as few-shot learning, unsupervised learning, representation learning, deep networks, meta-learning, visual recognition, semi-supervised learning, and clustering analysis.

  • Transfer Learning
  • Domain Adaptation
  • Few-Shot Learning
  • Unsupervised Learning
  • Representation Learning
  • Deep Networks
  • Meta-Learning
  • Visual Recognition
  • Semi-Supervised Learning
  • Clustering Analysis
Research works
23k
fractional, since 1951
In the world top 10%
2.2k
per year above
Top-10% rate
9.7%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+93%
the tick is no change
Largest producer
China
63% of the 10 largest, 2022-now
Domain Adaptation and Few-Shot Learning

Which countries lead Domain Adaptation and Few-Shot Learning research?

By volume, China and the United States publish the most (7.4k and 1.6k works in 2022-now).

By volume, 2022-now

  1. 1 China 7.4k works
  2. 2 United States 1.6k works
  3. 3 India 509 works
  4. 4 South Korea 463 works
  5. 5 United Kingdom 405 works
  6. 6 Germany 331 works
  7. 7 Australia 307 works
  8. 8 Japan 286 works
  9. 9 Canada 237 works
  10. 10 Singapore 222 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 62.7%United States: 13.7%India: 4.3%South Korea: 3.9%6 others listed: 15.3%63%largest
China7,352 · 62.7%United States1,611 · 13.7%India509 · 4.3%South Korea463 · 3.9%6 others listed1,788 · 15.3%

Shares of the rows listed above, not of the whole node.

Which institutions lead Domain Adaptation and Few-Shot Learning research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Domain Adaptation and Few-Shot Learning research, followed by University of Electronic Science and Technology of China and Xidian University.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 313 works
  2. 2 University of Electronic Science and Technology of ChinaChina 157 works
  3. 3 Xidian UniversityChina 144 works
  4. 4 Tsinghua UniversityChina 132 works
  5. 5 Zhejiang UniversityChina 127 works
  6. 6 National University of Defense TechnologyChina 125 works
  7. 7 Shanghai Jiao Tong UniversityChina 117 works
  8. 8 Peking UniversityChina 112 works
  9. 9 University of Science and Technology of ChinaChina 111 works
  10. 10 University of Chinese Academy of SciencesChina 110 works

Who are the leading researchers in Domain Adaptation and Few-Shot Learning?

The most-cited researchers publishing on Domain Adaptation and Few-Shot Learning include Kaiming He, Yoshua Bengio and Geoffrey E. Hinton.

  1. 1 Kaiming He Israel 562k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Geoffrey E. Hinton Canada 454k citations
  4. 4 Robert John Tibshirani United States 396k citations
  5. 5 Shaoqing Ren China 356k citations
  6. 6 Ross Girshick Israel 356k citations
  7. 7 Xiangyu Zhang 327k citations
  8. 8 Trevor Hastie United States 301k citations
  9. 9 Jian Sun 281k citations
  10. 10 Xiaogang Wang China 260k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Domain Adaptation and Few-Shot Learning?

The most cited paper in Domain Adaptation and Few-Shot Learning is "Deep Residual Learning for Image Recognition" (Kaiming He, Xiangyu Zhang, Shaoqing Ren et al., 2016), with 229,585 citations. Next come "Long Short-Term Memory" (102,418) and "ImageNet classification with deep convolutional neural networks" (75,634).

Most cited papers
#PaperReleasedCitations
1 Deep Residual Learning for Image Recognition Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. Conference paperOpen access Jun 2016 229,585
2 Long Short-Term Memory Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation Nov 1997 102,418
3 ImageNet classification with deep convolutional neural networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM Open access 24 May 2017 75,634
4 Going deeper with convolutions Christian Szegedy, Wei Liu, Yangqing Jia et al. Conference paper Jun 2015 47,422
5 Densely Connected Convolutional Networks Gao Ming Huang, Zhuang Liu, Laurens van der Maaten et al. Conference paper Jul 2017 45,976
All 97 most cited papers, with filters and sorting

Where is Domain Adaptation and Few-Shot Learning research done?

The largest centres of Domain Adaptation and Few-Shot Learning research in 2022-now are Beijing (China), Shanghai (China), Xi'an (China) and Nanjing (China). Among places with at least 20 works in it, it is an unusually large share of all research in Shanghai, Shenzhen and Mountain View.

Largest cities, 2022-now

  1. 1 BeijingChina 1.5k works
  2. 2 ShanghaiChina 515 works
  3. 3 Xi'anChina 454 works
  4. 4 NanjingChina 414 works
  5. 5 GuangzhouChina 339 works
  6. 6 HangzhouChina 303 works
  7. 7 ChengduChina 301 works
  8. 8 ShenzhenChina 297 works
  9. 9 WuhanChina 281 works
  10. 10 SeoulSouth Korea 255 works

Where it is the local speciality

  1. Shanghai21.0 works12×
  2. ShenzhenCN · 296.9 works6.7×
  3. Mountain ViewUS · 39.3 works5.8×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Domain Adaptation and Few-Shot Learning than the world average.

See Domain Adaptation and Few-Shot Learning on the map

Where is the best place to study Domain Adaptation and Few-Shot Learning?

Among universities, judged by research, Nanyang Technological University, Northwestern Polytechnical University and Hong Kong University of Science and Technology score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%10%20%mean 15.72%fractional works in this field (log) →share of work in the world top 10% →Hong Kong University…Nanyang Technologica…Northwestern Polytec…University of Hong K…
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Nanyang Technological UniversitySingapore 84.318.2%8.6×79 +52.4%
2Northwestern Polytechnical UniversityChina 79.917.2%8.2×107 +143.7%
3Hong Kong University of Science and TechnologyChina 79.518.4%9.0×42 +95.4%
4University of Hong KongChina 79.117.1%4.4×46 +260.8%
5National University of SingaporeSingapore 77.316.9%4.7×64 +111.8%
6Xidian UniversityChina 77.014.4%17.3×144 +211.0%
7Chinese University of Hong KongChina 76.917.2%4.7×39 +30.4%
8Tsinghua UniversityChina 74.113.8%5.0×132 +14.2%
9University of Electronic Science and Technology of ChinaChina 72.711.2%12.3×157 +87.1%
10Peking UniversityChina 72.012.8%4.8×112 +70.7%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Domain Adaptation and Few-Shot Learning, country by country

Is Domain Adaptation and Few-Shot Learning research growing?

Output in 2022-2025 was 93% higher than in 2018-2021, peaking in 2023. The fastest-growing topics are Domain Adaptation and Few-Shot Learning.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Domain Adaptation and Few-Shot Learning as a percentage of every work published that year, 0.040% in 2024.

still counting0.025%0.050%0.075%Domain Adaptation and Few-Shot Learning0.050% in 202519801990200020102020

Fractional works of Domain Adaptation and Few-Shot Learning over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Domain Adaptation and Few-Shot Learning9.8% in 202520102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Discussion

Ask a question or share a note about Domain Adaptation and Few-Shot Learning. Posts are plain text and can be reported.