Paper ｜ ArcFace: Additive Angular Margin Loss for Deep Face Recognition

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 $W \in R^{d \times n}$ 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:

最后编辑于：2023.10.25 16:25:25

©著作权归作者所有,转载或内容合作请联系作者
【社区内容提示】社区部分内容疑似由AI辅助生成，浏览时请结合常识与多方信息审慎甄别。
平台声明：文章内容（如有图片或视频亦包括在内）由作者上传并发布，文章内容仅代表作者本人观点，简书系信息发布平台，仅提供信息存储服务。