ArcFace: Additive Angular Margin Loss for Deep Face Recognition

01/23/2018
by   Jiankang Deng, et al.
0

Convolutional neural networks have significantly boosted the performance of face recognition in recent years due to its high capacity in learning discriminative features. To enhance the discriminative power of the Softmax loss, multiplicative angular margin and additive cosine margin incorporate angular margin and cosine margin into the loss functions, respectively. In this paper, we propose a novel supervisor signal, additive angular margin (ArcFace), which has a better geometrical interpretation than supervision signals proposed so far. Specifically, the proposed ArcFace cos(θ + m) directly maximise decision boundary in angular (arc) space based on the L2 normalised weights and features. Compared to multiplicative angular margin cos(mθ) and additive cosine margin cosθ-m, ArcFace can obtain more discriminative deep features. We also emphasise the importance of network settings and data refinement in the problem of deep face recognition. Extensive experiments on several relevant face recognition benchmarks, LFW, CFP and AgeDB, prove the effectiveness of the proposed ArcFace. Most importantly, we get state-of-art performance in the MegaFace Challenge in a totally reproducible way. We make data, models and training/test code public available [https://github.com/deepinsight/insightface].

READ FULL TEXT
research
01/29/2018

CosFace: Large Margin Cosine Loss for Deep Face Recognition

Face recognition has achieved revolutionary advancement owing to the adv...
research
01/17/2018

Additive Margin Softmax for Face Verification

In this paper, we propose a conceptually simple and geometrically interp...
research
09/12/2021

SphereFace Revived: Unifying Hyperspherical Face Recognition

This paper addresses the deep face recognition problem under an open-set...
research
10/10/2022

BoundaryFace: A mining framework with noise label self-correction for Face Recognition

Face recognition has made tremendous progress in recent years due to the...
research
09/29/2021

Improvising the Learning of Neural Networks on Hyperspherical Manifold

The impact of convolution neural networks (CNNs) in the supervised setti...
research
03/25/2019

Noise-Tolerant Paradigm for Training Face Recognition CNNs

Benefit from large-scale training datasets, deep Convolutional Neural Ne...
research
08/18/2023

Deep Boosting Multi-Modal Ensemble Face Recognition with Sample-Level Weighting

Deep convolutional neural networks have achieved remarkable success in f...

Please sign up or login with your details

Forgot password? Click here to reset