Tri-training
Tri-Training is a semi-supervised learning framework in which three diverse models are iteratively trained on labeled data and subsequently leverage unlabeled data by mutually providing pseudo-labels to enhance each other’s generalization.
46
Publications
3.9K
Citations
160
Authors
68
Institutions
Publications per year
2017–2026
25
Parents
46
An extensive experimental comparison of methods for multi-label learning
Gjorgji Madjarov, Dragi Kocev, Dejan Gjorgjevikj et al. · Pattern Recognition · 2012 · 731 citations
Tri-net for Semi-Supervised Deep Learning
Dongdong Chen, Wei Wang, Wei Gao et al. · 2018 · 145 citations
1–5 of 46
160
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 160
68
Nanjing University
Nanjing, China
4 h-index
13 publications
3.3K citations
China University of Mining and Technology
Xuzhou, China
3 h-index
11 publications
216 citations
Tsinghua University
Beijing, China
2 h-index
6 publications
99 citations

Xidian University
Xi'an, China
2 h-index
6 publications
249 citations
The University of Tokyo
Tokyo, Japan
2 h-index
6 publications
1.4K citations

Chinese Academy of Sciences
Beijing, China
2 h-index
8 publications
154 citations
University of Copenhagen
Copenhagen, Denmark
2 h-index
3 publications
119 citations

Harbin Institute of Technology
Harbin, China
2 h-index
7 publications
160 citations
1–8 of 68
2 publications · 30 citations
2
h-index
2 publications · 42 citations
2
h-index
Repository · 2 publications · 462 citations
2
h-index
1 publications · 20 citations
1
h-index
1 publications · 30 citations
1
h-index
1–5