Margin-based Loss
Margin-Based Loss is a type of loss function in machine learning that penalizes predictions based on the margin between the confidence scores of correct and incorrect classifications, differing from other loss functions by explicitly enforcing a separation boundary to enhance generalization.
264
Publications
21.7K
Citations
770
Authors
275
Institutions
Publications per year
2017–2026
170
Variants
Margin Loss
Parents
264
CosFace: Large Margin Cosine Loss for Deep Face Recognition
Hao Wang, Yitong Wang, Zheng Zhou et al. · 2018 · 2.9K citations
Additive Margin Softmax for Face Verification
IEEE Signal Processing Letters · 2018 · 1.1K citations · Full text
Deep Learning using Linear Support Vector Machines
Yichuan Tang · arXiv (Cornell University) · 2013 · 741 citations · Full text
A Comprehensive Survey of Loss Functions in Machine Learning
Qi Wang, Yue Ma, Kun Zhao et al. · Annals of Data Science · 2020 · 693 citations
1–5 of 264
770
5
h-index
4
h-index
4
h-index
4
h-index
4
h-index
1–5 of 770
275

Chinese Academy of Sciences
Beijing, China
13 h-index
40 publications
3.1K citations
Tsinghua University
Beijing, China
11 h-index
32 publications
1.5K citations
University of Chinese Academy of Sciences
Beijing, China
11 h-index
27 publications
3K citations
Google (United States)
Mountain View, United States
7 h-index
12 publications
419 citations
Institute of Automation
Beijing, China
7 h-index
14 publications
748 citations
Institute of Computing Technology
Beijing, China
6 h-index
20 publications
828 citations
Tencent (China)
Shenzhen, China
5 h-index
27 publications
26.6K citations

University of Minnesota
Minneapolis, United States
5 h-index
8 publications
318 citations
1–8 of 275
Repository · 52 publications · 3.4K citations
25
h-index
Conference · 8 publications · 624 citations
8
h-index
TPAMI · 6 publications · 309 citations
7
h-index
7 publications · 280 citations
7
h-index
Conference · 5 publications · 818 citations
5
h-index
1–5