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.

/pdf/arcface-additive-angular-margin-loss-for-deep-face-7vvlem659h.pdf

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.

Deep face recognition: A survey

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recently, the idea of mining-based strategies is adopted to emphasize the misclassified samples, achieving promising results. However, during the entire training process, the prior methods either do not explicitly emphasize the sample based on its importance that renders the hard samples not fully exploited; or explicitly emphasize the effects of semi-hard/hard samples even at the early training stage that may lead to convergence issue. In this work, we propose a novel Adaptive Curriculum Learning loss (CurricularFace) that embeds the idea of curriculum learning into the loss function to achieve a novel training strategy for deep face recognition, which mainly addresses easy samples in the early training stage and hard ones in the later stage. Specifically, our CurricularFace adaptively adjusts the relative importance of easy and hard samples during different training stages. In each stage, different samples are assigned with different importance according to their corresponding difficultness. Extensive experimental results on popular benchmarks demonstrate the superiority of our CurricularFace over the state-of-the-art competitors.

/pdf/curricularface-adaptive-curriculum-learning-loss-for-deep-2e0lhhnjfh.pdf

CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

A survey on deep learning based face recognition

Labeled Faces in the Wild (LFW) database has been widely utilized as the benchmark of unconstrained face verification and due to big data driven machine learning methods, the performance on the database approaches nearly 100%. However, we argue that this accuracy may be too optimistic because of some limiting factors. Besides different poses, illuminations, occlusions and expressions, cross-age face is another challenge in face recognition. Different ages of the same person result in large intra-class variations and aging process is unavoidable in real world face verification. However, LFW does not pay much attention on it. Thereby we construct a Cross-Age LFW (CALFW) which deliberately searches and selects 3,000 positive face pairs with age gaps to add aging process intra-class variance. Negative pairs with same gender and race are also selected to reduce the influence of attribute difference between positive/negative pairs and achieve face verification instead of attributes classification. We evaluate several metric learning and deep learning methods on the new database. Compared to the accuracy on LFW, the accuracy drops about 10%-17% on CALFW.

Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments

While very promising results have been shown on face recognition related problems, age-invariant face recognition still remains a challenge. Facial appearance of a person changes over time, which results in significant intraclass variations. In order to address this problem, we propose a novel deep face recognition network called age estimation guided convolutional neural network (AE-CNN) to separate the variations caused by aging from the personspecific features which are stable. The carefully designed CNN model can learn age-invariant features for face recognition. To the best of our knowledge, this is the first attempt to use age estimation task for obtaining age-invariant features. Extensive results on two well-known public domain face aging datasets: MORPH Album 2 and CACD show the effectiveness of the proposed approach.

/pdf/age-estimation-guided-convolutional-neural-network-for-age-1oms5fi164.pdf

Age Estimation Guided Convolutional Neural Network for Age-Invariant Face Recognition

Optical camera communication (OCC) enabled by LED and embedded cameras has attracted extensive attention, thanks to its rich spectrum availability and ready deployability. However, the close interactions between OCC and the indoor spaces have created two major challenges. On one hand, the stripe pattern incurred by OCC may greatly damage the accuracy of image-based object recognition. On the other hand, the patterns inherent to indoor spaces can significantly degrade the decoding performance of reflected OCC. To this end, we propose CORE-Lens as a pipeline to make the mutual interference transparent to existing OR and OCC algorithms. Essentially, CORE-Lens treats the two challenges as two sides of a signal mixture issue: the signals transmitted by OCC get mixed with background images so well that their features become entangled. Consequently, CORE-Lens exploits the idea of disentangled representation learning to separate the mixed signals in the feature space: while the GAN-reconstructed clean background images are used to perform object recognition, OCC decoding is conducted on the residual of the original image after subtracting the reconstructed background. Our extensive experiments on evaluating the real-life performance of CORE-Lens evidently demonstrate its superiority over conventional approaches.

/pdf/core-lens-simultaneous-communication-and-object-recognition-1oxymgi5.pdf

CORE-lens: simultaneous communication and object recognition with disentangled-GAN cameras

Continuous respiration monitoring is significant for real-life healthcare applications, but realizing it is extremely hard as wearable sensors are cumbersome and contact-free sensors largely fail to tolerate user movements. Meanwhile, tracking users indoors mostly demands user-held devices, while device-free localization can barely tell what and who it tracks. Fortunately, as both contact-free respiration monitoring and device-free localization may rely on Radio-Frequency (RF) sensing, fusing them together creates a novel system capable of continuously tracking users while recovering their fine-grained respiratory waveforms. To this end, we propose BreathCatcher as a continuous human respiration tracking system for indoor applications. To build this system, we employ commercial-grade compact radar pairs to capture RF reflections containing respiratory signals. We then propose a hybrid human respiration and position tracking algorithm to locate and identify respiratory signals from complex RF reflection mixtures. Finally, we design an encoder-decoder deep neural network driven by variational inference to recover fine-grained respiratory waveforms. Essentially, BreathCatcher cannot only obtain respiratory waveforms from multiple walking users, but also identify each user according to the latent properties of the respiratory signals. We evidently demonstrate the accuracy of both tracking and respiration monitoring via experiments involving 12 subjects and 80 man-hour data. 

Catch Your Breath: Simultaneous RF Tracking and Respiration Monitoring with Radar Pairs

Human age can provide important demographic information. In this paper, we tackle the estimation of age in face images with probabilities. The design of the proposed method is based on the relative order of age labels in the database. The age estimation problem is transformed into a series of binary classifications achieved by convolution neural network. Each classifier is used to judge whether the age of input image is larger than a certain age and the estimated age is obtained by adding probability values of these classification problems. The proposed method: Deep Probabilities (DP) of facial age shows improvements over direct regression and multi-classification methods.

Tianyue Zheng

Papers

Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments

Age Estimation Guided Convolutional Neural Network for Age-Invariant Face Recognition

CORE-lens: simultaneous communication and object recognition with disentangled-GAN cameras

Catch Your Breath: Simultaneous RF Tracking and Respiration Monitoring with Radar Pairs

Deep probabilities for age estimation