A Comprehensive Study on Face Recognition Biases Beyond Demographics
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；Technical University of Darmstadt（达姆施塔特工业大学）；Universidad Autonoma de Madrid（马德里自治大学）
Philipp Terhörst, Jan Niklas Kolf, Marco Huber, Florian Kirchbuchner, Naser Damer, Aythami Morales, Julian Fierrez, Arjan Kuijper
备注：
Under review in IEEE Transactions on Technology and Society
Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. However, to enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR beyond demographics. Therefore, in this work, we analyse FR bias over a wide range of attributes. We investigate the influence of 47 attributes on the verification performance of two popular FR models. The experiments were performed on the publicly available MAADFace attribute database with over 120M high-quality attribute annotations. To prevent misleading statements about biased performances, we introduced control group based validity values to decide if unbalanced test data causes the performance differences. The results demonstrate that also many non-demographic attributes strongly affect the recognition performance, such as accessories, hair-styles and colors, face shapes, or facial anomalies. The observations of this work show the strong need for further advances in making FR system more robust, explainable, and fair. Moreover, our findings might help to a better understanding of how FR networks work, to enhance the robustness of these networks, and to develop more generalized bias-mitigating face recognition solutions.
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…
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）
Face quality assessment aims at estimating the utility of a face image for the purpose of recognition. It is a key factor to achieve high face recognition performances. Currently, the high performance of these face recognition systems come with the cost of a strong bias against demographic and non-demographic sub-groups. Recent work has shown that face quality assessment algorithms should adapt to the deployed face recognition system, in order to achieve highly accurate and robust quality estimations. However, this could lead to a bias transfer towards the face quality assessment leading to di…
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 discriminati…
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形学研究所IGD）；TU Darmstadt（达姆施塔特工业大学）
Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the inherent biases in these solutions and to make them more transparent to the public and developers. In this work, we aim at providing a set of explainability tool that analyse the difference in the face recognition models' behaviors when processing different demographic groups. We do that by leveraging higher-order statistical information based on activation map…
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形学研究所IGD）；Technical University of Darmstadt（达姆施塔特工业大学）
Current face recognition systems achieve high progress on several benchmark tests. Despite this progress, recent works showed that these systems are strongly biased against demographic sub-groups. Consequently, an easily integrable solution is needed to reduce the discriminatory effect of these biased systems. Previous work mainly focused on learning less biased face representations, which comes at the cost of a strongly degraded overall recognition performance. In this work, we propose a novel unsupervised fair score normalization approach that is specifically designed to reduce the effect of…
Face biometrics are playing a key role in making modern smart city applications more secure and usable. Commonly, the recognition threshold of a face recognition system is adjusted based on the degree of security for the considered use case. The likelihood of a match can be for instance decreased by setting a high threshold in case of a payment transaction verification. Prior work in face recognition has unfortunately showed that error rates are usually higher for certain demographic groups. These disparities have hence brought into question the fairness of systems empowered with face biometri…
Tencent（腾讯）；Nanjing University of Science and Technology（南京理工大学）
Demographic bias is a significant challenge in practical face recognition systems. Existing methods heavily rely on accurate demographic annotations. However, such annotations are usually unavailable in real scenarios. Moreover, these methods are typically designed for a specific demographic group and are not general enough. In this paper, we propose a false positive rate penalty loss, which mitigates face recognition bias by increasing the consistency of instance False Positive Rate (FPR). Specifically, we first define the instance FPR as the ratio between the number of the non-target similar…
On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes
Paderborn University（帕德博恩大学）；Technical University of Darmstadt（达姆施塔特技术大学）；University of Notre Dame（诺特丹大学）；Johannes Gutenberg University Mainz（美因茨约翰· Gutenberg大学）
University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；University of Michigan（密歇根大学）
The proliferation of automated face recognition in the commercial and government sectors has caused significant privacy concerns for individuals. One approach to address these privacy concerns is to employ evasion attacks against the metric embedding networks powering face recognition systems: Face obfuscation systems generate imperceptibly perturbed images that cause face recognition systems to misidentify the user. Perturbed faces are generated on metric embedding networks, which are known to be unfair in the context of face recognition. A question of demographic fairness naturally follows: …
Microsoft AI R&D Center, Taiwan（台湾微软人工智能研发中心）；National Tsing Hua University（国立清华大学）
Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evalua…
Universidad Autonoma de Madrid（马德里自治大学）；Max Planck Institute for Human Development（马克斯·普朗克人类发展研究所）
The most popular face recognition benchmarks assume a distribution of subjects without much attention to their demographic attributes. In this work, we perform a comprehensive discrimination-aware experimentation of deep learning-based face recognition. The main aim of this study is focused on a better understanding of the feature space generated by deep models, and the performance achieved over different demographic groups. We also propose a general formulation of algorithmic discrimination with application to face biometrics. The experiments are conducted over the new DiveFace database compo…
Recently, different researchers have found that the gallery composition of a face database can induce performance differentials to facial identification systems in which a probe image is compared against up to all stored reference images to reach a biometric decision. This negative effect is referred to as "watchlist imbalance effect". In this work, we present a method to theoretically estimate said effect for a biometric identification system given its verification performance across demographic groups and the composition of the used gallery. Further, we report results for identification expe…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）；Michigan State University（密歇根州立大学）
Impact due to demographic factors such as age, sex, race, etc., has been studied extensively in automated face recognition systems. However, the impact of \textit{digitally modified} demographic and facial attributes on face recognition is relatively under-explored. In this work, we study the effect of attribute manipulations induced via generative adversarial networks (GANs) on face recognition performance. We conduct experiments on the CelebA dataset by intentionally modifying thirteen attributes using AttGAN and STGAN and evaluating their impact on two deep learning-based face verification …
Hochschule Darmstadt（达姆施塔特应用技术大学）；University of Salzburg（萨尔茨堡大学）
Recently, concerns regarding potential biases in the underlying algorithms of many automated systems (including biometrics) have been raised. In this context, a biased algorithm produces statistically different outcomes for different groups of individuals based on certain (often protected by anti-discrimination legislation) attributes such as sex and age. While several preliminary studies investigating this matter for facial recognition algorithms do exist, said topic has not yet been addressed for vascular biometric characteristics. Accordingly, in this paper, several popular types of recogni…
Facial recognition technology and human raters can predict political orientation from images of expressionless faces even when controlling for demographics and self-presentation
Université Paris-Saclay（巴黎萨克雷大学）；CEA（法国原子能和替代能源委员会）；University Politehnica of Bucharest（布加勒斯特理工大学）
Face verification aims to distinguish between genuine and imposter pairs of faces, which include the same or different identities, respectively. The performance reported in recent years gives the impression that the task is practically solved. Here, we revisit the problem and argue that existing evaluation datasets were built using two oversimplifying design choices. First, the usual identity selection to form imposter pairs is not challenging enough because, in practice, verification is needed to detect challenging imposters. Second, the underlying demographics of existing datasets are often …
Can Vision Transformers with ResNet's Global Features Fairly Authenticate Demographic Faces?
National Research Council of Italy - Institute of Applied Sciences and Intelligent Systems (CNR-ISASI)（意大利国家研究 council - 应用科学和智能系统研究所（CNR-ISASI））；University of Gour Banga（Gour Banga 大学）；Visva-Bharati（Visva-Bharati 研究院）
Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction
Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid（智能人工智能部门，马德里理工大学）；Departamento de Informática y Estadística, Universidad Rey Juan Carlos（信息与统计学部门，皇家胡安·卡洛斯大学）；ELLIS Unit Madrid（马德里ELLIS单位）
Imperial College London（帝国理工学院）；University of Athens（雅典大学）
Deep learning-based methods have pushed the limits of the state-of-the-art in face analysis. However, despite their success, these models have raised concerns regarding their bias towards certain demographics. This bias is inflicted both by limited diversity across demographics in the training set, as well as the design of the algorithms. In this work, we investigate the demographic bias of deep learning models in face recognition, age estimation, gender recognition and kinship verification. To this end, we introduce the most comprehensive, large-scale dataset of facial images and videos to da…
We demonstrate an approach to face attribute detection that retains or improves attribute detection accuracy across gender and race subgroups by learning demographic information prior to learning the attribute detection task. The system, which we call InclusiveFaceNet, detects face attributes by transferring race and gender representations learned from a held-out dataset of public race and gender identities. Leveraging learned demographic representations while withholding demographic inference from the downstream face attribute detection task preserves potential users' demographic privacy whil…
Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance by providing additional information about sample quality. Because FIQA methods attempt to estimate the utility of a sample for face recognition, it is reasonable to assume that these methods are heavily influenced by the underlying face recognition system. Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias. It is therefore likely that such problems are also present with FIQA techniques. To investiga…
BenchX: Benchmarking AI Models for Cancer Detection and Localization with Demographic and Protocol Biases
Johns Hopkins University（约翰霍普金斯大学）；German Cancer Research Center（德国癌症研究中心）；University Hospital Basel（巴塞尔大学医院）；University of Zurich（苏黎世大学）；ETH AI Center（苏黎世联邦理工学院AI中心）；Istanbul Medipol University（伊斯坦布尔梅迪波尔大学）；Stanford University（斯坦福大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Nanyang Technological University（南洋理工大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；University of California, San Francisco（加州大学旧金山分校）；Johns Hopkins Medicine（约翰霍普金斯医学）
