ArcFace swMATH ID: 33958 Software Authors: Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou Description: 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. Homepage: https://arxiv.org/abs/1801.07698 Related Software: PyTorch; LFW; FaceNet; SphereFace; DeepFace; ShuffleNet; VGGFace2; MegaFace; EfficientNet; Face2Face; Inception-v4; ImageNet; DeepLab; InfoGAN; RetinaFace; DARTS; MS-COCO; CosFace; FaceX-Zoo; AdaCos Cited in: 6 Documents all top 5 Cited by 20 Authors 1 Fierrez, Julian 1 Han, Feng 1 Li, Jingyu 1 Luo, Ping 1 Morales, Aythami 1 Obradovich, Nick 1 Ren, Jiamin 1 Savchenko, Andrey V. 1 Serna, Ignacio 1 Shao, Wenqi 1 Shen, Furao 1 Szeliski, Richard 1 Wang, Huijiao 1 Wang, Xiaogang 1 Wang, Xudong 1 Yang, Xulei 1 Yu, Lei 1 Zhang, Haijian 1 Zhang, Ruimao 1 Zhao, Jian all top 5 Cited in 6 Serials 1 Artificial Intelligence 1 Multidimensional Systems and Signal Processing 1 Journal of Mathematical Sciences (New York) 1 International Journal of Computer Vision 1 The Journal of Artificial Intelligence Research (JAIR) 1 Texts in Computer Science Cited in 3 Fields 5 Computer science (68-XX) 1 Statistics (62-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year