No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Deep Face Recognition Based on Penalty Cosface
Abstract
Face recognition has achieved great progress because of the advancement of deep convolutional neural networks (CNNs) techniques. The Softmax loss is one of the most popular loss function for deep learning models. In many situations, face images are captured in the unconstrained environments with changing poses and illuminations, making face recognition very challenging because of the dramatic appearance variations. The models trained with the Softmax loss may fail to extract discriminative information for the face images with extreme illumination or pose conditions. Recently, Cosface has been proven effective for improving the generalization ability of the Softmax loss. Derived from Cosface, we propose a novel method named Penalty Cosface to address the unconstrained face recognition challenges and learn discriminative features. Specifically, we design a variant of Cosface that remove radial variations by penalizing \(\ell _2\)-normalized constraints of the features and weights. Therefore, the discriminative ability of the Penalty Cosface is guaranteed by the large margin of the Cosface, and the penalty term is beneficial to simplifying the gradient calculations. Experimental results show that the Penalty Cosface improves the discriminative power of deep networks and outperforms the other variants of Softmax loss.
ResearchGate has not been able to resolve any citations for this publication.
In this paper, we propose a conceptually simple and geometrically interpretable objective function, i.e. additive margin Softmax (AM-Softmax), for deep face verification. In general, the face verification task can be viewed as a metric learning problem, so learning large-margin face features whose intra-class variation is small and inter-class difference is large is of great importance in order to achieve good performance. Recently, Large-margin Softmax and Angular Softmax have been proposed to incorporate the angular margin in a multiplicative manner. In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works. We also emphasize and discuss the importance of feature normalization in the paper. Most importantly, our experiments on LFW BLUFR and MegaFace show that our additive margin softmax loss consistently performs better than the current state-of-the-art methods using the same network architecture and training dataset. Our code has also been made available at https://github.com/happynear/AMSoftmax
In this paper, we introduce a new large-scale face dataset named VGGFace2. The dataset contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession (e.g. actors, athletes, politicians). The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise. We describe how the dataset was collected, in particular the automated and manual filtering stages to ensure a high accuracy for the images of each identity. To assess face recognition performance using the new dataset, we train ResNet-50 (with and without Squeeze-and-Excitation blocks) Convolutional Neural Networks on VGGFace2, on MS- Celeb-1M, and on their union, and show that training on VGGFace2 leads to improved recognition performance over pose and age. Finally, using the models trained on these datasets, we demonstrate state-of-the-art performance on the IJB-A and IJB-B face recognition benchmarks, exceeding the previous state-of-the-art by a large margin. Datasets and models are publicly available.
Over the last few years, increased interest has arisen with respect to age-related tasks in the Computer Vision community. As a result, several "in-the-wild" databases annotated with respect to the age attribute became available in the literature. Nevertheless, one major drawback of these databases is that they are semi-automatically collected and annotated and thus they contain noisy labels. Therefore, the algorithms that are evaluated in such databases are prone to noisy estimates. In order to overcome such drawbacks, we present in this paper the first, to the best of knowledge, manually collected "in-the-wild" age database, dubbed AgeDB, containing images annotated with accurate to the year, noise-free labels. As demonstrated by a series of experiments utilizing state-of-the-art algorithms, this unique property renders AgeDB suitable when performing experiments on age-invariant face verification, age estimation and face age progression "in-the-wild".
This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific $m$ to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge 1 show the superiority of A-Softmax loss in FR tasks.
The state-of-the-art of face recognition has been significantly advanced by
the emergence of deep learning. Very deep neural networks recently achieved
great success on general object recognition because of their superb learning
capacity. This motivates us to investigate their effectiveness on face
recognition. This paper proposes two very deep neural network architectures,
referred to as DeepID3, for face recognition. These two architectures are
rebuilt from stacked convolution and inception layers proposed in VGG net and
GoogLeNet to make them suitable to face recognition. Joint face
identification-verification supervisory signals are added to both intermediate
and final feature extraction layers during training. An ensemble of the
proposed two architectures achieves 99.53% LFW face verification accuracy and
96.0% LFW rank-1 face identification accuracy, respectively. A further
discussion of LFW face verification result is given in the end.
Pushing by big data and deep convolutional neural network (CNN), the
performance of face recognition is becoming comparable to human. Using private
large scale training datasets, several groups achieve very high performance on
LFW, i.e., 97% to 99%. While there are many open source implementations of CNN,
none of large scale face dataset is publicly available. The current situation
in the field of face recognition is that data is more important than algorithm.
To solve this problem, this paper proposes a semi-automatical way to collect
face images from Internet and builds a large scale dataset containing about
10,000 subjects and 500,000 images, called CASIAWebFace. Based on the database,
we use a 11-layer CNN to learn discriminative representation and obtain
state-of-theart accuracy on LFW and YTF. The publication of CASIAWebFace will
attract more research groups entering this field and accelerate the development
of face recognition in the wild.
The key challenge of face recognition is to develop effective feature
representations for reducing intra-personal variations while enlarging
inter-personal differences. In this paper, we show that it can be well solved
with deep learning and using both face identification and verification signals
as supervision. The Deep IDentification-verification features (DeepID2) are
learned with carefully designed deep convolutional networks. The face
identification task increases the inter-personal variations by drawing DeepID2
extracted from different identities apart, while the face verification task
reduces the intra-personal variations by pulling DeepID2 extracted from the
same identity together, both of which are essential to face recognition. The
learned DeepID2 features can be well generalized to new identities unseen in
the training data. On the challenging LFW dataset, 99.15% face verification
accuracy is achieved. Compared with the best deep learning result on LFW, the
error rate has been significantly reduced by 67%.
Automatic facial expression analysis is an interesting and challenging problem, and impacts important applications in many areas such as human–computer interaction and data-driven animation. Deriving an effective facial representation from original face images is a vital step for successful facial expression recognition. In this paper, we empirically evaluate facial representation based on statistical local features, Local Binary Patterns, for person-independent facial expression recognition. Different machine learning methods are systematically examined on several databases. Extensive experiments illustrate that LBP features are effective and efficient for facial expression recognition. We further formulate Boosted-LBP to extract the most discriminant LBP features, and the best recognition performance is obtained by using Support Vector Machine classifiers with Boosted-LBP features. Moreover, we investigate LBP features for low-resolution facial expression recognition, which is a critical problem but seldom addressed in the existing work. We observe in our experiments that LBP features perform stably and robustly over a useful range of low resolutions of face images, and yield promising performance in compressed low-resolution video sequences captured in real-world environments.
We present a class of extremely efficient CNN models, MobileFaceNets, which use less than 1 million parameters and are specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. We first make a simple analysis on the weakness of common mobile networks for face verification. The weakness has been well overcome by our specifically designed MobileFaceNets. Under the same experimental conditions, our MobileFaceNets achieve significantly superior accuracy as well as more than 2 times actual speedup over MobileNetV2. After trained by ArcFace loss on the refined MS-Celeb-1 M, our single MobileFaceNet of 4.0 MB size achieves 99.55% accuracy on LFW and 92.59% TAR@FAR1e-6 on MegaFace, which is even comparable to state-of-the-art big CNN models of hundreds MB size. The fastest one of MobileFaceNets has an actual inference time of 18 ms on a mobile phone. For face verification, MobileFaceNets achieve significantly improved efficiency over previous state-of-the-art mobile CNNs.
In this paper, we present a class of extremely efficient CNN models called MobileFaceNets, which use no more than 1 million parameters and specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. We also make a simple analysis on the weakness of common mobile networks for face verification. The weakness has been well overcome by our specifically designed MobileFaceNets. Under the same experimental conditions, our MobileFaceNets achieve significantly superior accuracy as well as more than 2 times actual speedup over MobileNetV2. After trained by ArcFace loss on the refined MS-Celeb-1M from scratch, our single MobileFaceNet model of 4.0MB size achieves 99.55% face verification accuracy on LFW and 92.59% TAR (FAR1e-6) on MegaFace Challenge 1, which is even comparable to state-of-the-art big CNN models of hundreds MB size. The fastest one of our MobileFaceNets has an actual inference time of 18 milliseconds on a mobile phone. Our experiments on LFW, AgeDB, and MegaFace show that our MobileFaceNets achieve significantly improved efficiency compared with the state-of-the-art lightweight and mobile CNNs for face verification.
Numerical Optimization presents a comprehensive and up-to-date description of the most effective methods in continuous optimization. It responds to the growing interest in optimization in engineering, science, and business by focusing on the methods that are best suited to practical problems.
For this new edition the book has been thoroughly updated throughout. There are new chapters on nonlinear interior methods and derivative-free methods for optimization, both of which are used widely in practice and the focus of much current research. Because of the emphasis on practical methods, as well as the extensive illustrations and exercises, the book is accessible to a wide audience. It can be used as a graduate text in engineering, operations research, mathematics, computer science, and business. It also serves as a handbook for researchers and practitioners in the field. The authors have strived to produce a text that is pleasant to read, informative, and rigorous - one that reveals both the beautiful nature of the discipline and its practical side.
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively.
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 dif- ferent classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implemen- tation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called dropout that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss can be optimized by typical stochastic gradient descent. Extensive experiments on four benchmark datasets demonstrate that the deeply-learned features with L-softmax loss become more discriminative, hence significantly boosting the performance on a variety of visual classification and verification tasks.
Convolutional neural networks (CNNs) have been widely used in computer vision community, significantly improving the state-of-the-art. In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model. In order to enhance the discriminative power of the deeply learned features, this paper proposes a new supervision signal, called center loss, for face recognition task. Specifically, the center loss simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers. More importantly, we prove that the proposed center loss function is trainable and easy to optimize in the CNNs. With the joint supervision of softmax loss and center loss, we can train a robust CNNs to obtain the deep features with the two key learning objectives, inter-class dispension and intra-class compactness as much as possible, which are very essential to face recognition. It is encouraging to see that our CNNs (with such joint supervision) achieve the state-of-the-art accuracy on several important face recognition benchmarks, Labeled Faces in the Wild (LFW), YouTube Faces (YTF), and MegaFace Challenge. Especially, our new approach achieves the best results on MegaFace (the largest public domain face benchmark) under the protocol of small training set (contains under 500000 images and under 20000 persons), significantly improving the previous results and setting new state-of-the-art for both face recognition and face verification tasks.
Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this paper, we propose a deep cascaded multi-task framework which exploits the inherent correlation between them to boost up their performance. In particular, our framework adopts a cascaded structure with three stages of carefully designed deep convolutional networks that predict face and landmark location in a coarse-to-fine manner. In addition, in the learning process, we propose a new online hard sample mining strategy that can improve the performance automatically without manual sample selection. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging FDDB and WIDER FACE benchmark for face detection, and AFLW benchmark for face alignment, while keeps real time performance.
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---8x deeper than VGG nets 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 competitions,
where we also won the 1st places on the tasks of ImageNet detection, ImageNet
localization, COCO detection, and COCO segmentation.
We introduce Adam, an algorithm for first-order gradient-based optimization
of stochastic objective functions. The method is straightforward to implement
and is based an adaptive estimates of lower-order moments of the gradients. The
method is computationally efficient, has little memory requirements and is well
suited for problems that are large in terms of data and/or parameters. The
method is also ap- propriate for non-stationary objectives and problems with
very noisy and/or sparse gradients. The method exhibits invariance to diagonal
rescaling of the gradients by adapting to the geometry of the objective
function. The hyper-parameters have intuitive interpretations and typically
require little tuning. Some connections to related algorithms, on which Adam
was inspired, are discussed. We also analyze the theoretical convergence
properties of the algorithm and provide a regret bound on the convergence rate
that is comparable to the best known results under the online convex
optimization framework. We demonstrate that Adam works well in practice when
experimentally compared to other stochastic optimization methods.
In this work we investigate the effect of the convolutional network depth on
its accuracy in the large-scale image recognition setting. Our main
contribution is a thorough evaluation of networks of increasing depth, which
shows that a significant improvement on the prior-art configurations can be
achieved by pushing the depth to 16-19 weight layers. These findings were the
basis of our ImageNet Challenge 2014 submission, where our team secured the
first and the second places in the localisation and classification tracks
respectively.
In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep network involves more than 120 million parameters using several locally connected layers without weight sharing, rather than the standard convolutional layers. Thus we trained it on the largest facial dataset to-date, an identity labeled dataset of four million facial images belonging to more than 4,000 identities, where each identity has an average of over a thousand samples. The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.25% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 25%, closely approaching human-level performance.
Dynamic texture (DT) is an extension of texture to the temporal domain. Description and recognition of DTs have attracted growing attention. In this paper, a novel approach for recognizing DTs is proposed and its simplifications and extensions to facial image analysis are also considered. First, the textures are modeled with volume local binary patterns (VLBP), which are an extension of the LBP operator widely used in ordinary texture analysis, combining motion and appearance. To make the approach computationally simple and easy to extend, only the co-occurrences of the local binary patterns on three orthogonal planes (LBP-TOP) are then considered. A block-based method is also proposed to deal with specific dynamic events such as facial expressions in which local information and its spatial locations should also be taken into account. In experiments with two DT databases, DynTex and Massachusetts Institute of Technology (MIT), both the VLBP and LBP-TOP clearly outperformed the earlier approaches. The proposed block-based method was evaluated with the Cohn-Kanade facial expression database with excellent results. The advantages of our approach include local processing, robustness to monotonic gray-scale changes, and simple computation.
Labeled faces in the wild: a database for studying face recognition in unconstrained environments
- G B Huang
- M Ramesh
- T Berg
- E Learned-Miller