Face recognition is known to exhibit bias - subjects in a certain demographic group can be better recognized than other groups. This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our proposed group adaptive classifier mitigates bias by using adaptive convolution kernels and attention mechanisms on faces based on their demographic attributes. The adaptive module comprises kernel masks and channel-wise attention maps for each demographic group so as to activate different facial regions for identification, leading to more discriminative features pertinent to their demographics. Our introduced automated adaptation strategy determines whether to apply adaptation to a certain layer by iteratively computing the dissimilarity among demographic-adaptive parameters. A new de-biasing loss function is proposed to mitigate the gap of average intra-class distance between demographic groups. Experiments on face benchmarks (RFW, LFW, IJB-A, and IJB-C) show that our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland, College Park（马里兰大学学院公园分校）
State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to identifying faces. However, the implicit encoding of gender information in face descriptors has two major issues: (a.) It makes the descriptors susceptible to privacy leakage, i.e. a malicious agent can be trained to predict the face gender from such descriptors. (b.) It appears to contribute to gender bias in face recognition, i.e. we find a significant difference in the recognition accuracy of DCNNs on male and female f…
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, \ie, high variations in size and sparsity, of the clusters. Consequently, the conventional way of using a uniform threshold (to identify clusters) often leads to a terrible misclassification for the samples that should belong to hard clusters. We tackle this problem by leveraging the neighborhood information of samples and inferring the cluster mem…
No single classifier can alone solve the complex problem of face recognition. Researchers found that combining some base classifiers usually enhances their recognition rate. The weaknesses of the base classifiers are reflected on the resulting combined system. In this work, a system for combining unstable, low performance classifiers is proposed. The system is applied to face images of 392 persons. The system shows remarkable stability and high recognition rate using a reduced number of parameters. The system illustrates the possibility of designing a combined system that benefits from the str…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland, College Park（马里兰大学学院公园分校）
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears to contribute to bias in face recognition. However, existing bias mitigation approaches generally require end-to-end training and are unable to achieve high verification accuracy. Therefore, we present a descriptor-based adversarial de-biasing approach called `Protected Attribute Suppression System (PASS)'. PASS can be trained on top of descriptors obtained…
Despite outstanding performance on public benchmarks, face recognition still suffers due to domain mismatch between training (source) and testing (target) data. Furthermore, these domains are not shared classes, which complicates domain adaptation. Since this is also a fine-grained classification problem which does not strictly follow the low-density separation principle, conventional domain adaptation approaches do not resolve these problems. In this paper, we formulate domain mismatch in face recognition as a style mismatch problem for which we propose two methods. First, we design a domain …
University of Sassari（萨萨里大学）；Jadavpur University（贾达夫普尔大学）；I.I.T Kanpur（印度理工学院坎普尔分校）
Faces are highly deformable objects which may easily change their appearance over time. Not all face areas are subject to the same variability. Therefore decoupling the information from independent areas of the face is of paramount importance to improve the robustness of any face recognition technique. This paper presents a robust face recognition technique based on the extraction and matching of SIFT features related to independent face areas. Both a global and local (as recognition from parts) matching strategy is proposed. The local strategy is based on matching individual salient facial SI…
Center for Pattern Recognition and Machine Intelligence, PES University（PES大学模式识别与机器智能中心）
The paper posits a computationally-efficient algorithm for multi-class facial image classification in which images are constrained with translation, rotation, scale, color, illumination and affine distortion. The proposed method is divided into five main building blocks including Haar-Cascade for face detection, Bilateral Filter for image preprocessing to remove unwanted noise, Affine Speeded-Up Robust Features (ASURF) for keypoint detection and description, Vector of Locally Aggregated Descriptors (VLAD) for feature quantization and Cloud Forest for image classification. The proposed method a…
Thermal infra-red (IR) images focus on changes of temperature distribution on facial muscles and blood vessels. These temperature changes can be regarded as texture features of images. A comparative study of face recognition methods working in thermal spectrum is carried out in this paper. In these study two local-matching methods based on Haar wavelet transform and Local Binary Pattern (LBP) are analyzed. Wavelet transform is a good tool to analyze multi-scale, multi-direction changes of texture. Local binary patterns (LBP) are a type of feature used for classification in computer vision. Fir…
CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61）；Cyber Security Cooperative Research Centre（网络安全合作研究中心）
Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep learning is widely utilized for face recognition (FR); however, such models are vulnerable to backdoor attacks executed by malicious parties. Backdoor attacks cause a model to misclassify a particular class as a target class during recognition. This vulnerability can allow adversaries to gain access to highly sensitive data protected by biometric authenticatio…
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 (DebFace) 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…
The datasets of face recognition contain an enormous number of identities and instances. However, conventional methods have difficulty in reflecting the entire distribution of the datasets because a mini-batch of small size contains only a small portion of all identities. To overcome this difficulty, we propose a novel method called BroadFace, which is a learning process to consider a massive set of identities, comprehensively. In BroadFace, a linear classifier learns optimal decision boundaries among identities from a large number of embedding vectors accumulated over past iterations. By refe…
This paper demonstrates two different fusion techniques at two different levels of a human face recognition process. The first one is called data fusion at lower level and the second one is the decision fusion towards the end of the recognition process. At first a data fusion is applied on visual and corresponding thermal images to generate fused image. Data fusion is implemented in the wavelet domain after decomposing the images through Daubechies wavelet coefficients (db2). During the data fusion maximum of approximate and other three details coefficients are merged together. After that Prin…
Mitigating Bias: Enhancing Image Classification by Improving Model Explanations
Amirkabir University of Technology（阿米尔卡比尔理工大学）；Okinawa Institute of Science and Technology（冲绳科学技术大学院大学）；Institute for Research in Fundamental Sciences（基础科学研究所）
CUNY City College（纽约市立大学城市学院）；Graduate Center（研究生中心）
We propose a deep learning-based feature fusion approach for facial computing including face recognition as well as gender, race and age detection. Instead of training a single classifier on face images to classify them based on the features of the person whose face appears in the image, we first train four different classifiers for classifying face images based on race, age, gender and identification (ID). Multi-task features are then extracted from the trained models and cross-task-feature training is conducted which shows the value of fusing multimodal features extracted from multi-tasks. W…
Jiangnan University（江南大学）；University of Surrey（萨里大学）
In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification. In contrast to traditional dictionary learning methods, NRDL investigates the use of non-negative representation (NR), which contributes to learning discriminative dictionary atoms. In order to make the learned dictionary more suitable for classification, NRDL seamlessly incorporates nonnegative representation constraint, discriminative dictionary learning and linear classifier training into a unified model. Specifically, NRDL introduces a pos…
The traditional approach to face anti-spoofing sees it as a binary classification problem, and binary classifiers are trained and validated on specialized anti-spoofing databases. One of the drawbacks of this approach is that, due to the variability of face spoofing attacks, environmental factors, and the typically small sample size, such classifiers do not generalize well to previously unseen databases. Anomaly detection, which approaches face anti-spoofing as a one-class classification problem, is emerging as an increasingly popular alternative approach. Nevertheless, in all existing work on…
Universidad Autonoma de Madrid（马德里自治大学）；Universitat Oberta de Catalunya（加泰罗尼亚开放大学）
This work explores facial expression bias as a security vulnerability of face recognition systems. Despite the great performance achieved by state-of-the-art face recognition systems, the algorithms are still sensitive to a large range of covariates. We present a comprehensive analysis of how facial expression bias impacts the performance of face recognition technologies. Our study analyzes: i) facial expression biases in the most popular face recognition databases; and ii) the impact of facial expression in face recognition performances. Our experimental framework includes two face detectors,…
An automatic Facial Expression Recognition (FER) model with Adaboost face detector, feature selection based on manifold learning and synergetic prototype based classifier has been proposed. Improved feature selection method and proposed classifier can achieve favorable effectiveness to performance FER in reasonable processing time.
University of North Carolina Wilmington（北卡罗来纳大学威尔明顿分校）；Elon University（埃隆大学）；Emory University（埃默里大学）
Aging or gender variation can affect the face recognition performance dramatically. While most of the face recognition studies are focused on the variation of pose, illumination and expression, it is important to consider the influence of gender effect and how to design an effective matching framework. In this paper, we address these problems on a very large longitudinal database MORPH-II which contains 55,134 face images of 13,617 individuals. First, we consider four comprehensive experiments with different combination of gender distribution and subset size, including: 1) equal gender distrib…
NEC Biometrics Research Laboratories（NEC生物识别研究实验室）；NEC Corporation（NEC公司）
In light of the rising demand for biometric-authentication systems, preventing face spoofing attacks is a critical issue for the safe deployment of face recognition systems. Here, we propose an efficient face presentation attack detection (PAD) algorithm that requires minimal hardware and only a small database, making it suitable for resource-constrained devices such as mobile phones. Utilizing one monocular visible light camera, the proposed algorithm takes two facial photos, one taken with a flash, the other without a flash. The proposed $SpecDiff$ descriptor is constructed by leveraging two…
This paper proposes a novel face recognition algorithm based on large-scale supervised hierarchical feature learning. The approach consists of two parts: hierarchical feature learning and large-scale model learning. The hierarchical feature learning searches feature in three levels of granularity in a supervised way. First, face images are modeled by receptive field theory, and the representation is an image with many channels of Gaussian receptive maps. We activate a few most distinguish channels by supervised learning. Second, the face image is further represented by patches of picked channe…
This paper proposes the use of a discrete cosine transform (DCT) instead of the eigenfaces method (Karhunen-Loeve Transform) for biometric identification based on frontal face images. Experimental results show better recognition accuracies and reduced computational burden. This paper includes results with different classifiers and a combination of them.
Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation provide equal and unbiased performance across subgroups. However, \textit{can seemingly unbiased pre-trained model become biased when input data undergoes certain distortions?} For the first time, we attempt to answer this question in the context of face recognition. We provide a systematic analysis to evaluate the performance of four state-of-the-art deep face re…
Beijing University of Posts and Telecommunications（北京邮电大学）；AI Labs, Didi Chuxing（滴滴出行AI实验室）
In order to make facial features more discriminative, some new models have recently been proposed. However, almost all of these models use the traditional face verification method, where the cosine operation is performed using the features of the bottleneck layer output. However, each of these models needs to change a threshold each time it is operated on a different test set. This is very inappropriate for application in real-world scenarios. In this paper, we train a validation classifier to normalize the decision threshold, which means that the result can be obtained directly without replac…
Although biometric facial recognition systems are fast becoming part of security applications, these systems are still vulnerable to morphing attacks, in which a facial reference image can be verified as two or more separate identities. In border control scenarios, a successful morphing attack allows two or more people to use the same passport to cross borders. In this paper, we propose a novel differential morph attack detection framework using a deep Siamese network. To the best of our knowledge, this is the first research work that makes use of a Siamese network architecture for morph attac…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；Intelligent Systems Lab（智能系统实验室）；Huawei Moscow Research Center（华为莫斯科研究中心）
Recent works showed the vulnerability of image classifiers to adversarial attacks in the digital domain. However, the majority of attacks involve adding small perturbation to an image to fool the classifier. Unfortunately, such procedures can not be used to conduct a real-world attack, where adding an adversarial attribute to the photo is a more practical approach. In this paper, we study the problem of real-world attacks on face recognition systems. We examine security of one of the best public face recognition systems, LResNet100E-IR with ArcFace loss, and propose a simple method to attack i…
Applications such as face recognition that deal with high-dimensional data need a mapping technique that introduces representation of low-dimensional features with enhanced discriminatory power and a proper classifier, able to classify those complex features. Most of traditional Linear Discriminant Analysis suffer from the disadvantage that their optimality criteria are not directly related to the classification ability of the obtained feature representation. Moreover, their classification accuracy is affected by the "small sample size" problem which is often encountered in FR tasks. In this s…
Michigan State University（密歇根州立大学）；University of Wisconsin – Madison（威斯康星大学麦迪逊分校）
Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual's face image with high accuracy. However, this raises privacy concerns, especially when face images collected for biometric recognition purposes are used for attribute analysis without the person's consent. To address this problem, we develop a technique for imparting soft biometric privacy to face images via an image perturbation methodology. The image perturbation is undertaken using a GAN-based Semi-Adversarial Network (SAN) - referred to as PrivacyNet - that…
Web-based technology has improved drastically in the past decade. As a result, security technology has become a major help to protect our daily life. In this paper, we propose a robust security based on face recognition system (SoF). In particular, we develop this system to giving access into a home for authenticated users. The classifier is trained by using a new adaptive learning method. The training data are initially collected from social networks. The accuracy of the classifier is incrementally improved as the user starts using the system. A novel method has been introduced to improve the…
Non-frontal face recognition using GANs and memristor-based classifiers
Centre for Electronics Frontiers, Institute for Integrated Micro and Nano Systems, School of Engineering, The University of Edinburgh（爱丁堡大学工程学院集成微纳系统研究所电子前沿中心）
Deep Learning methods have become state-of-the-art for solving tasks such as Face Recognition (FR). Unfortunately, despite their success, it has been pointed out that these learning models are exposed to adversarial inputs - images to which an imperceptible amount of noise for humans is added to maliciously fool a neural network - thus limiting their adoption in real-world applications. While it is true that an enormous effort has been spent in order to train robust models against this type of threat, adversarial detection techniques have recently started to draw attention within the scientifi…
University of Brasilia（巴西利亚大学）；CIC / IE / UnB（巴西利亚大学计算与信息中心/工程研究所）；Vicon Motion Systems Ltd（维康运动系统有限公司）
In this paper, we evaluate the effects of occlusions in the performance of a face recognition pipeline that uses a ResNet backbone. The classifier was trained on a subset of the CelebA-HQ dataset containing 5,478 images from 307 classes, to achieve top-1 error rate of 17.91%. We designed 8 different occlusion masks which were applied to the input images. This caused a significant drop in the classifier performance: its error rate for each mask became at least two times worse than before. In order to increase robustness under occlusions, we followed two approaches. The first is image inpainting…
Beijing Institute of Technology（北京理工大学）；NanKai University（南开大学）
The popular softmax loss and its recent extensions have achieved great success in the deep learning-based image classification. However, the data for training image classifiers usually has different quality. Ignoring such problem, the correct classification of low quality data is hard to be solved. In this paper, we discover the positive correlation between the feature norm of an image and its quality through careful experiments on various applications and various deep neural networks. Based on this finding, we propose a contraction mapping function to compress the range of feature norms of tr…
Microsoft（微软）；IIT Kanpur（印度理工学院坎普尔分校）；Oracle（甲骨文公司）；University of Bath（巴斯大学）
Understanding unsupervised domain adaptation has been an important task that has been well explored. However, the wide variety of methods have not analyzed the role of a classifier's performance in detail. In this paper, we thoroughly examine the role of a classifier in terms of matching source and target distributions. We specifically investigate the classifier ability by matching a) the distribution of features, b) probabilistic uncertainty for samples and c) certainty activation mappings. Our analysis suggests that using these three distributions does result in a consistently improved perfo…
NortonLifeLock Research Group（NortonLifeLock研究集团）；Carnegie Mellon University（卡内基梅隆大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
This paper proposes a new defense called $n$-ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers. Inspired by $n$-version programming, $n$-ML trains an ensemble of $n$ classifiers, and inputs are classified by a vote of the classifiers in the ensemble. Unlike prior such approaches, however, the classifiers in the ensemble are trained specifically to classify adversarial examples differently, rendering it very difficult for an adversarial example to obtain enough votes to be misclassified. We show that $n…
Privacy concerns in the modern digital age have prompted researchers to develop techniques that allow users to selectively suppress certain information in collected data while allowing for other information to be extracted. In this regard, Semi-Adversarial Networks (SAN) have recently emerged as a method for imparting soft-biometric privacy to face images. SAN enables modifications of input face images so that the resulting face images can still be reliably used by arbitrary conventional face matchers for recognition purposes, while attribute classifiers, such as gender classifiers, are confou…
Columbia University（哥伦比亚大学）；Rutgers University（罗格斯大学）
Machine learning has been used to recognize emotions in faces, typically by looking for 8 different emotional states (neutral, happy, sad, surprise, fear, disgust, anger and contempt). We consider two approaches: feature recognition based on facial landmarks and deep learning on all pixels; each produced 58% overall accuracy. However, they produced different results on different images and thus we propose a new meta-classifier combining these approaches. It produces far better results with 77% accuracy
Recent research has proposed the use of Semi Adversarial Networks (SAN) for imparting privacy to face images. SANs are convolutional autoencoders that perturb face images such that the perturbed images cannot be reliably used by an attribute classifier (e.g., a gender classifier) but can still be used by a face matcher for matching purposes. However, the generalizability of SANs across multiple arbitrary gender classifiers has not been demonstrated in the literature. In this work, we tackle the generalization issue by designing an ensemble SAN model that generates a diverse set of perturbed ou…
Microsoft Research（微软研究院）；Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However, generating counterfactual examples for images is non-trivial due to the underlying causal structure on the various features of an image. To be meaningful, generated perturbations need to satisfy constraints implied by the causal model. We present a method for generating counterfactuals by incorporating a structural causal model (SCM) in an improved variant of Adversa…
Johns Hopkins University（约翰斯·霍普金斯大学）；Univ. of Maryland, College Park（马里兰大学帕克分校）；NIST（美国国家标准与技术研究院）
Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the face that a network attends to vary by the category of an attribute. This might contribute to bias. Building on this intuition, we propose a novel distillation-based approach called Distill and De-bias (D&D) to enforce a network to attend to similar face regions, irrespective of the attribute category. In D&D, we train a teacher network on images from one category of an attribute; e.g. light skintone. Then distilling in…
YITU Technology（依图科技）；Northeastern University of China（中国东北大学）
Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the student model (i.e. to make images corresponding to the same semantics share the same embedding across different models). In this work, we focus on its application in face recognition. We observe that existing knowledge distillation models optimize the proxy tasks that force the student to mimic the teacher's behavior, instead of directly optimizing the face …
Recently, Adaboost has been widely used to improve the accuracy of any given learning algorithm. In this paper we focus on designing an algorithm to employ combination of Adaboost with Support Vector Machine as weak component classifiers to be used in Face Detection Task. To obtain a set of effective SVM-weaklearner Classifier, this algorithm adaptively adjusts the kernel parameter in SVM instead of using a fixed one. Proposed combination outperforms in generalization in comparison with SVM on imbalanced classification problem. The proposed here method is compared, in terms of classification a…
