ArcFace: Additive Angular Margin Loss for Deep Face Recognition
15 Jun 2019-pp 4690-4699
TL;DR: 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.
Citations
More filters
12 May 2019
TL;DR: In this article, a self-attentive residual network, an angular margin loss function and adversarial training strategy are combined to learn extremely compact, 64-dimensional speaker embeddings for text-independent speaker verification.
Abstract: In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging, real-world problem in biometric security. We further the development of end-to-end speaker embedding models by combing a novel 1-dimensional, self-attentive residual network, an angular margin loss function and adversarial training strategy. Our model is able to learn extremely compact, 64-dimensional speaker embeddings that deliver competitive performance on a number of popular datasets using simple cosine distance scoring. One the NIST-SRE 2016 task we are able to beat a strong i-vector baseline, while on the Speakers in the Wild task our model was able to outperform both i-vector and x-vector baselines, showing an absolute improvement of 2.19% over the latter. Additionally, we show that the integration of adversarial training consistently leads to a significant improvement over an unadapted model.
28 citations
01 Jan 2021
TL;DR: In this article, identity information in face images can flow from the training corpus into synthetic samples without any adversarial actions when building or using the existing model, which raises privacy-related questions, but also stimulates discussions of how to create generative models that do not inadvertently reveal identity information of real subjects whose images were used for training.
Abstract: Generative adversarial networks (GANs) are able to generate high resolution photo-realistic images of objects that "do not exist." These synthetic images are rather difficult to detect as fake. However, the manner in which these generative models are trained hints at a potential for information leakage from the supplied training data, especially in the context of synthetic faces. This paper presents experiments suggesting that identity information in face images can flow from the training corpus into synthetic samples without any adversarial actions when building or using the existing model. This raises privacy-related questions, but also stimulates discussions of (a) the face manifold’s characteristics in the feature space and (b) how to create generative models that do not inadvertently reveal identity information of real subjects whose images were used for training. We used five different face matchers (face_recognition, FaceNet, ArcFace, SphereFace and Neurotechnology MegaMatcher) and the StyleGAN2 synthesis model, and show that this identity leakage does exist for some, but not all methods. So, can we say that these synthetically generated faces truly do not exist? Databases of real and synthetically generated faces are made available with this paper to allow full replicability of the results discussed in this work.
28 citations
Posted Content•
TL;DR: In this article, a meta-learning approach is proposed to initialize the parameters of both the generator and discriminator in a person-specific way, so that training can be based on just a few images and done quickly.
Abstract: Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many practical scenarios, such personalized talking head models need to be learned from a few image views of a person, potentially even a single image. Here, we present a system with such few-shot capability. It performs lengthy meta-learning on a large dataset of videos, and after that is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators. Crucially, the system is able to initialize the parameters of both the generator and the discriminator in a person-specific way, so that training can be based on just a few images and done quickly, despite the need to tune tens of millions of parameters. We show that such an approach is able to learn highly realistic and personalized talking head models of new people and even portrait paintings.
28 citations
Posted Content•
19 Nov 2019
TL;DR: A novel de-biasing adversarial network that learns to extract disentangled feature representations for both unbiased face recognition and demographics estimation and a new scheme to combine demographics with identity features to strengthen robustness of face representation in different demographic groups is designed.
Abstract: We address the problem of bias in automated face recognition and demographic attribute estimation algorithms, where errors are lower on certain cohorts belonging to specific demographic groups. We present a novel de-biasing adversarial network that learns to extract disentangled feature representations for both unbiased face recognition and demographics estimation. The proposed network consists of one identity classifier and three demographic classifiers (for gender, age, and race) that are trained to distinguish identity and demographic attributes, respectively. Adversarial learning is adopted to minimize correlation among feature factors so as to abate bias influence from other factors. We also design a new scheme to combine demographics with identity features to strengthen robustness of face representation in different demographic groups. The experimental results show that our approach is able to reduce bias in face recognition as well as demographics estimation while achieving state-of-the-art performance.
27 citations
Cites methods from "ArcFace: Additive Angular Margin Lo..."
...To be specific, CACD [8], IMDB [40], UTKFace [60], AgeDB [35], AFAD [38], AAF [9], FG-NET 3, RFW [52], IMFDB-CVIT [42], AsianDeepGlint [1], and PCSO [11] are the datasets for training and testing models of demographic estimations; and the datasets for learning and evaluating models of face verification are MS-Celeb-1M [17], LFW [24], IJB-A [28], and IJB-C [34]....
[...]
...EFeat is trained on MS-Celeb-1M by SGD with a learning rate of 0.01....
[...]
...We keep the hyper-parameter setting of AM-Softmax as [12]: s = 64 and m = 0....
[...]
...Since there is no demographic labels in MS-Celeb-1M, we first train three demographic estimation models for gender, age, and race, respectively....
[...]
...We predict the demographic labels of MS-Celeb-1M with the well-trained demographic models....
[...]
TL;DR: Tuming et al. as mentioned in this paper proposed a method that takes advantage of the combination of deep learning and Local Binary Pattern (LBP) features to recognize the masked face by utilizing RetinaFace, a joint extra-supervised and self-vised multi-task learning face detector.
Abstract: Face recognition is one of the most common biometric authentication methods as its feasibility while convenient use. Recently, the COVID-19 pandemic is dramatically spreading throughout the world, which seriously leads to negative impacts on people's health and economy. Wearing masks in public settings is an effective way to prevent viruses from spreading. However, masked face recognition is a highly challenging task due to the lack of facial feature information. In this paper, we propose a method that takes advantage of the combination of deep learning and Local Binary Pattern (LBP) features to recognize the masked face by utilizing RetinaFace, a joint extra-supervised and self-supervised multi-task learning face detector that can deal with various scales of faces, as a fast yet effective encoder. In addition, we extract local binary pattern features from masked face's eye, forehead and eyebow areas and combine them with features learnt from RetinaFace into a unified framework for recognizing masked faces. In addition, we collected a dataset named COMASK20 from 300 subjects at our institution. In the experiment, we compared our proposed system with several state of the art face recognition methods on the published Essex dataset and our self-collected dataset COMASK20. With the recognition results of 87% f1-score on the COMASK20 dataset and 98% f1-score on the Essex dataset, these demonstrated that our proposed system outperforms Dlib and InsightFace, which has shown the effectiveness and suitability of the proposed method. The COMASK20 dataset is available on https://github.com/tuminguyen/COMASK20 for research purposes.
27 citations
References
More filters
27 Jun 2016
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.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
Journal Article•
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.
Abstract: Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show 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.
33,597 citations
Proceedings Article•
06 Jul 2015TL;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.
Abstract: Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. 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. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.
30,843 citations
28 Oct 2017
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.
Abstract: In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models. It builds upon a few projects, most notably Lua Torch, Chainer, and HIPS Autograd [4], and provides a high performance environment with easy access to automatic differentiation of models executed on different devices (CPU and GPU). To make prototyping easier, PyTorch does not follow the symbolic approach used in many other deep learning frameworks, but focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead. Note that this preprint is a draft of certain sections from an upcoming paper covering all PyTorch features.
13,268 citations
Posted Content•
TL;DR: The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.
Abstract: TensorFlow is an interface for expressing machine learning algorithms, and an
implementation for executing such algorithms. A computation expressed using
TensorFlow can be executed with little or no change on a wide variety of
heterogeneous systems, ranging from mobile devices such as phones and tablets
up to large-scale distributed systems of hundreds of machines and thousands of
computational devices such as GPU cards. The system is flexible and can be used
to express a wide variety of algorithms, including training and inference
algorithms for deep neural network models, and it has been used for conducting
research and for deploying machine learning systems into production across more
than a dozen areas of computer science and other fields, including speech
recognition, computer vision, robotics, information retrieval, natural language
processing, geographic information extraction, and computational drug
discovery. This paper describes the TensorFlow interface and an implementation
of that interface that we have built at Google. The TensorFlow API and a
reference implementation were released as an open-source package under the
Apache 2.0 license in November, 2015 and are available at www.tensorflow.org.
10,447 citations