Instance-based Transfer
Instance-Based Transfer is a transfer learning approach that belongs to the category of methods leveraging source domain instances directly in the target domain learning process, distinguished by reusing or reweighting actual data instances from the source domain rather than transferring model parameters or feature representations.
62
Publications
2.9K
Citations
249
Authors
115
Institutions
Publications per year
2017–2026
46
Variants
Instance-based Transfer Learning
Parents
62
Tingting Li, Ruihe Qian, Chao Dong et al. · 2018 · 249 citations
Knowledge Transfer for Rotary Machine Fault Diagnosis
Fei Shen, Chuang Sun, Xuefeng Chen · IEEE Sensors Journal · 2019 · 243 citations
Multi-Domain Neural Machine Translation through Unsupervised Adaptation
M. Amin Farajian, Marco Turchi, Matteo Negri et al. · 2017 · 123 citations · Full text
Computing, Computer Science, Natural Language Processing +12
1–5 of 62
249
2
h-index
2
h-index
2
h-index
University of Maryland, Baltimore County, United States
2 publications · 101 citations
2
h-index
2
h-index
1–5 of 249
115

Chinese Academy of Sciences
Beijing, China
4 h-index
12 publications
560 citations

Beihang University
Beijing, China
3 h-index
4 publications
352 citations

Xi'an Jiaotong University
Xi'an, China
3 h-index
9 publications
885 citations

Beijing Institute of Technology
Beijing, China
3 h-index
11 publications
282 citations

Southeast University
Nanjing, China
2 h-index
4 publications
360 citations

Polish Academy of Sciences
Warsaw, Poland
2 h-index
2 publications
103 citations
University of Chinese Academy of Sciences
Beijing, China
2 h-index
6 publications
170 citations

Southwest Jiaotong University
Chengdu, China
2 h-index
7 publications
479 citations
1–8 of 115
2 publications · 59 citations
2
h-index
2 publications · 40 citations
2
h-index
2 publications · 95 citations
2
h-index
QJEP · 1 publications · 23 citations
1
h-index
1 publications · 18 citations
1
h-index
1–5