1 intro
- we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition.
existing loss:
softmax loss:
- the size of linear transformation matrix
increases linearly with the n;
- learned features are separable for closed-set classification problem but not discriminative enough for open-set face recognition.
triplet loss:
- leading to a significant increase in the number of iteration steps
- semi-hard sample mining is a quite difficult problem for effective model training.
2 this paper
Propose a new ArcFace loss:
code:
https://github.com/deepinsight/insightface
https://github.com/deepinsight/insightface/tree/c2db41402c627cab8ea32d55da591940f2258276/recognition/arcface_torch
https://github.com/TreB1eN/InsightFace_Pytorch
https://github.com/ronghuaiyang/arcface-pytorch
网友评论