scispace - formally typeset
Open AccessProceedings ArticleDOI

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

Reads0
Chats0
TLDR
This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead.
Abstract
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 can enhance the discriminative power. Centre loss penalises the distance between 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 the angular space and therefore penalises the angles between 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 its exact correspondence to geodesic distance on a hypersphere. We present arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks which includes a new large-scale image database with trillions 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. To facilitate future research, the code has been made available.

read more

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI

Whether normalized or not? Towards more robust iris recognition using dynamic programming

TL;DR: Wang et al. as discussed by the authors proposed a non-normalized preprocessing method based on dynamic path search for iris segmentation and employed a deep convolution network (DCNN) based on partial convolution operators to extract iris features.
Journal ArticleDOI

Human Activity Recognition Machine With an Anchor-Based Loss Function

- 01 Jan 2022 - 
TL;DR: Wang et al. as mentioned in this paper proposed a new clustering method based on the Euclidean distance for the pseudo open-set problem, which reduces the computation cost and improves the accuracy.
Proceedings ArticleDOI

Learning Disentangled Representations for Identity Preserving Surveillance Face Camouflage

TL;DR: Zhang et al. as discussed by the authors proposed an encoder-decoder network architecture which can separately disentangle the facial feature representation into an appearance code and an identification code, and then recombine the identity and appearance codes to synthesize a new face, which has the same identity as the source subject.
Book ChapterDOI

Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping

TL;DR: Wang et al. as discussed by the authors proposed an effective end-to-end unified framework to achieve both face reenactment and face swapping by disentangling identity and attribute unsupervisedly.
Journal ArticleDOI

AAN-Face: Attention Augmented Networks for Face Recognition

TL;DR: In this paper, an attention erasing (AE) scheme is proposed to randomly erase units in attention maps, and an attention center loss (ACL) is introduced to learn a center for each attention map, so that the same attention map focuses on the same facial part.
References
More filters
Proceedings ArticleDOI

Deep Residual Learning for Image Recognition

TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal Article

Dropout: a simple way to prevent neural networks from overfitting

TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings Article

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.

Automatic differentiation in PyTorch

TL;DR: An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.