ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Citations
3 citations
3 citations
3 citations
3 citations
3 citations
Cites methods from "ArcFace: Additive Angular Margin Lo..."
...Four experiments were conducted; comparison experiment with various hyperparameters was conducted to observe the change in accuracy rate caused by varying the ArcFace hyperparameters s and m; comparison experiment with conventional CapsNet confirmed the proposed method’s validity; visualisation experiment of the super-capsule demonstrated that the super-capsule of the proposed method distributed in whole feature space; image reconstruction experiment presented that CpasNet is not suitable for image reconstruction; The experiments were conducted using the MNIST, CIFAR10, and their deformed datasets....
[...]
...TABLE I, TABLE II present the change in accuracy rate caused by varying the ArcFace hyperparameters s and m....
[...]
...In the proposed method, we employ the ArcFace [7] metric learning loss function to calculate the similarity between a class representative vector and a single super-capsule....
[...]
...With this change, the margin loss is not available; thus, we also propose a new loss function based on ArcFace, a type of metric learning....
[...]
...9 presents an overview of ArcFace....
[...]
References
123,388 citations
33,597 citations
30,843 citations
13,268 citations
10,447 citations