Visual Transfer Learning
Visual Transfer Learning is a transfer learning paradigm that leverages knowledge acquired from a source visual domain to improve learning performance in a target visual domain with differing data distributions, thereby distinguishing itself by its focus on cross-domain visual representation adaptation.
212
Publications
22.2K
Citations
727
Authors
245
Institutions
Publications per year
2017–2026
168
Parents
212
Deep visual domain adaptation: A survey
Mei Wang, Weihong Deng · Neurocomputing · 2018 · 2.2K citations · Full text
Person Transfer GAN to Bridge Domain Gap for Person Re-identification
Longhui Wei, Shiliang Zhang, Wen Gao et al. · 2018 · 2K citations
Do Better ImageNet Models Transfer Better?
Simon Kornblith, Jonathon Shlens, Quoc V. Le · 2019 · 1.3K citations
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
Judy Hoffman, Eric Tzeng, Taesung Park et al. · arXiv (Cornell University) · 2017 · 630 citations · Full text
1–5 of 212
727
8
h-index
6
h-index
5
h-index
5
h-index
5
h-index
1–5 of 727
245
University of California, Berkeley
Berkeley, United States
12 h-index
28 publications
5.8K citations
Google (United States)
Mountain View, United States
11 h-index
38 publications
7K citations

Zhejiang University
Hangzhou, China
6 h-index
17 publications
1.3K citations
Stanford University
Stanford, United States
6 h-index
18 publications
1.1K citations
Beijing Academy of Artificial Intelligence
Beijing, China
5 h-index
15 publications
4.7K citations

Chinese Academy of Sciences
Beijing, China
5 h-index
15 publications
1.3K citations
Institute of Automation
Beijing, China
5 h-index
13 publications
916 citations
University of Illinois Urbana-Champaign
Urbana, United States
4 h-index
8 publications
283 citations
1–8 of 245
Repository · 54 publications · 3.8K citations
28
h-index
Conference · 8 publications · 361 citations
8
h-index
6 publications · 389 citations
6
h-index
Conference · 5 publications · 488 citations
5
h-index
TPAMI · 5 publications · 303 citations
5
h-index
1–5