ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Abstract

One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for largescale 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 Ar-cFace 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 1 , which will help reproduce the results in this paper. * denotes equal contribution to this work.

The Mertens Unrolled Network (MU-Net): A high dynamic range fusion neural network for through the windshield driver recognition

“…For each method, we detect faces using RetinaFace 31 and subsequently extract feature templates using Additive Angular Margin Loss for Deep Face Recognition (ArcFace). 32 Because our driver dataset is relatively small and was not used for network training, we report results over the entire set of subjects. Figure 7 Shows the final results of all 6 methods.…”

Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification

“…In the case of this version, after face detection and alignment, cleaning was performed by a semi-automatic refinement strategy. First, a pre-trained ArcFace model [10] was used to automatically remove outlier images of each identity. A manual removal of incorrectly labelled images by "ethnicity-specific annotators" followed to result in a dataset of 5,179,510 images of 93,431 identities.…”

“…We select the ArcFace model [10] to study in this work. ArcFace employs the Additive Angular Margin Loss and a ResNet100 backbone to arrive at a 512-dimensional feature representation of an input image.…”

Large-scale Multi-modal Person Identification in Real Unconstrained Environments

“…As deep learning has been developing rapidly in recent years, all these video understanding methods have achieved great success. In the field of face recognition, based on the LFW benchmark [1], ArcFace [11] realized a precision of 99.83%, which had exceeded the human performance. The best results on Megaface [2] also reached 99.39%.…”