ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Citations
14 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...The generated backbonemodel in the network was used in the same structure, when fine-tuned with the ArcFace....
[...]
...The hyper-parameters of the ArcFace, s and m, were set to 30 and 0.5, respectively, in Eq....
[...]
...[4] J. Deng, J. Guo, N. Xue, and S. Zafeiriou, ‘‘ArcFace: Additive angular margin loss for deep face recognition,’’ in Proc....
[...]
...LArcFace = − 1 N N∑ i=1 log es(cos(θyi+m)) es(cos(θyi+m)) + ∑n j=1,j6=yi e scosθj , (12) where N and n are the batch size and the class number, respectively. θyi is the target (groud truth) angle. m is the angular margin penalty and s is the feature scale....
[...]
...Deep neural network architectures [1], [2], creating novel loss functions [2]–[4], and large-scale face datasets [5]–[7] are the factors that made it possible to increase performance....
[...]
14 citations
14 citations
14 citations
References
123,388 citations
33,597 citations
30,843 citations
13,268 citations
10,447 citations