ArcFace
ArcFace: Additive Angular Margin Loss for Deep Face Recognition. One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power. Centre loss penalises the distance between the deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in an angular space and penalises the angles between the deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to the exact correspondence to the geodesic distance on the hypersphere. We present arguably the most extensive experimental evaluation of all the recent state-of-the-art face recognition methods on over 10 face recognition benchmarks including a new large-scale image database with trillion level of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state-of-the-art and can be easily implemented with negligible computational overhead. We release all refined training data, training codes, pre-trained models and training logs, which will help reproduce the results in this paper.
Keywords for this software
References in zbMATH (referenced in 5 articles )
Showing results 1 to 5 of 5.
Sorted by year (- Jun Wang, Yinglu Liu, Yibo Hu, Hailin Shi, Tao Mei: FaceX-Zoo: A PyTorch Toolbox for Face Recognition (2021) arXiv
- Qingzhong Wang, Pengfei Zhang, Haoyi Xiong, Jian Zhao: Face.evoLVe: A High-Performance Face Recognition Library (2021) arXiv
- Xingkun Xu, Yuge Huang, Pengcheng Shen, Shaoxin Li, Jilin Li, Feiyue Huang, Yong Li, Zhen Cui: Consistent Instance False Positive Improves Fairness in Face Recognition (2021) arXiv
- Lingxiao He, Xingyu Liao, Wu Liu, Xinchen Liu, Peng Cheng, Tao Mei: FastReID: A Pytorch Toolbox for General Instance Re-identification (2020) arXiv
- Shao, Wenqi; Li, Jingyu; Ren, Jiamin; Zhang, Ruimao; Wang, Xiaogang; Luo, Ping: SSN: learning sparse switchable normalization via SparsestMax (2020)