Name
Abstract | ||
|---|---|---|
Demographic bias is a significant challenge in practical face recognition systems. Existing methods heavily rely on accurate demographic annotations. However, such annotations are usually unavailable in real scenarios. Moreover, these methods are typically designed for a specific demographic group and are not general enough. In this paper, we propose a false positive rate penalty loss, which mitig... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPR46437.2021.00064 | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Keywords | DocType | ISSN |
Training,Computer vision,Codes,Annotations,Face recognition,Benchmark testing | Conference | 1063-6919 |
ISBN | Citations | PageRank |
978-1-6654-4509-2 | 2 | 0.38 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xingkun Xu | 1 | 2 | 0.38 |
| Yuge Huang | 2 | 5 | 1.42 |
| Pengcheng Shen | 3 | 50 | 4.47 |
| Shaoxin Li | 4 | 282 | 13.39 |
| Jilin Li | 5 | 48 | 8.94 |
| Feiyue Huang | 6 | 226 | 41.86 |
| Yong Li | 7 | 47 | 2.98 |
| Zhen Cui | 8 | 14 | 6.66 |