Triplet Loss
Triplet Loss is a loss function in metric learning that penalizes the relative distance between an anchor sample, a positive sample of the same class, and a negative sample of a different class by enforcing a margin-based separation in the embedding space.
614
Publications
45K
Citations
2.1K
Authors
580
Institutions
Publications per year
2017–2026
563
Parents
614
Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
De Cheng, Yihong Gong, Sanping Zhou et al. · 2016 · 1.3K citations
Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification
Weihua Chen, Xiaotang Chen, Jianguo Zhang et al. · 2017 · 1.2K citations
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Yifan Sun, Changmao Cheng, Yuhan Zhang et al. · 2020 · 921 citations
1–5 of 614
2.1K
6
h-index
6
h-index
4
h-index
4
h-index
4
h-index
1–5 of 2.1K
580
University of Chinese Academy of Sciences
Beijing, China
21 h-index
63 publications
10.2K citations

Chinese Academy of Sciences
Beijing, China
20 h-index
77 publications
7.6K citations

Beihang University
Beijing, China
16 h-index
49 publications
2.9K citations

Sun Yat-sen University
Guangzhou, China
13 h-index
37 publications
1.6K citations

Peking University
Beijing, China
13 h-index
31 publications
1.5K citations

Xidian University
Xi'an, China
13 h-index
43 publications
1.4K citations
University of Science and Technology of China
Hefei, China
12 h-index
30 publications
1.9K citations
Tsinghua University
Beijing, China
11 h-index
24 publications
2.8K citations
1–8 of 580
Repository · 55 publications · 6.2K citations
24
h-index
20 publications · 724 citations
18
h-index
18 publications · 1.3K citations
17
h-index
Conference · 16 publications · 849 citations
15
h-index
15 publications · 990 citations
14
h-index
1–5