Over the past decades the machine and deep learning community has celebrated great achievements in challenging tasks such as image classification. The deep architecture of artificial neural networks together with the plenitude of available data makes it possible to describe highly complex relations. Yet, it is still impossible to fully capture what the deep learning model has learned and to verify that it operates fairly and without creating bias, especially in critical tasks, for instance those arising in the medical field. One example for such a task is the detection of distinct facial expressions, called Action Units, in facial images. Considering this specific task, our research aims to provide transparency regarding bias, specifically in relation to gender and skin color. We train a neural network for Action Unit classification and analyze its performance quantitatively based on its accuracy and qualitatively based on heatmaps. A structured review of our results indicates that we are able to detect bias. Even though we cannot conclude from our results that lower classification performance emerged solely from gender and skin color bias, these biases must be addressed, which is why we end by giving suggestions on how the detected bias can be avoided.
National University of Singapore（新加坡国立大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Machine learning models automatically learn discriminative features from the data, and are therefore susceptible to learn strongly-correlated biases, such as using protected attributes like gender and race. Most existing bias mitigation approaches aim to explicitly reduce the model's focus on these protected features. In this work, we propose to mitigate bias by explicitly guiding the model's focus towards task-relevant features using domain knowledge, and we hypothesize that this can indirectly reduce the dependence of the model on spurious correlations it learns from the data. We explore bia…
Pontifícia Universidade Católica do Rio Grande do Sul（南里奥格兰德天主教大学）；Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）
Facial analysis models are increasingly applied in real-world applications that have significant impact on peoples' lives. However, as literature has shown, models that automatically classify facial attributes might exhibit algorithmic discrimination behavior with respect to protected groups, potentially posing negative impacts on individuals and society. It is therefore critical to develop techniques that can mitigate unintended biases in facial classifiers. Hence, in this work, we introduce a novel learning method that combines both subjective human-based labels and objective annotations bas…
Existing facial analysis systems have been shown to yield biased results against certain demographic subgroups. Due to its impact on society, it has become imperative to ensure that these systems do not discriminate based on gender, identity, or skin tone of individuals. This has led to research in the identification and mitigation of bias in AI systems. In this paper, we encapsulate bias detection/estimation and mitigation algorithms for facial analysis. Our main contributions include a systematic review of algorithms proposed for understanding bias, along with a taxonomy and extensive overvi…
In order to analyze a trained model performance and identify its weak spots, one has to set aside a portion of the data for testing. The test set has to be large enough to detect statistically significant biases with respect to all the relevant sub-groups in the target population. This requirement may be difficult to satisfy, especially in data-hungry applications. We propose to overcome this difficulty by generating synthetic test set. We use the face landmarks detection task to validate our proposal by showing that all the biases observed on real datasets are also seen on a carefully designe…
Centre for Vision, Speech and Signal Processing (CVSSP)（视觉、语音与信号处理中心（CVSSP））；University of Surrey（萨里大学）
The most existing studies in the facial age estimation assume training and test images are captured under similar shooting conditions. However, this is rarely valid in real-world applications, where training and test sets usually have different characteristics. In this paper, we advocate a cross-dataset protocol for age estimation benchmarking. In order to improve the cross-dataset age estimation performance, we mitigate the inherent bias caused by the learning algorithm itself. To this end, we propose a novel loss function that is more effective for neural network training. The relative smoot…
We report our investigation on the use of the popular PlantVillage dataset for training deep learning based plant disease detection models. We trained a machine learning model using only 8 pixels from the PlantVillage image backgrounds. The model achieved 49.0% accuracy on the held-out test set, well above the random guessing accuracy of 2.6%. This result indicates that the PlantVillage dataset contains noise correlated with the labels and deep learning models can easily exploit this bias to make predictions. Possible approaches to alleviate this problem are discussed.
The performance of a computer vision model depends on the size and quality of its training data. Recent studies have unveiled previously-unknown composition biases in common image datasets which then lead to skewed model outputs, and have proposed methods to mitigate these biases. However, most existing works assume that human-generated annotations can be considered gold-standard and unbiased. In this paper, we reveal that this assumption can be problematic, and that special care should be taken to prevent models from learning such annotation biases. We focus on facial expression recognition a…
Wichita State University（威奇托州立大学）；University of North Carolina Wilmington（北卡罗来纳大学威尔明顿分校）
Obesity is one of the most important public health problems that the world is facing today. A recent trend is in the development of intervention tools that predict BMI using facial images for weight monitoring and management to combat obesity. Most of these studies used BMI annotated facial image datasets that mainly consisted of Caucasian subjects. Research on bias evaluation of face-based gender-, age-classification, and face recognition systems suggest that these technologies perform poorly for women, dark-skinned people, and older adults. The bias of facial analysis-based BMI prediction to…
University of Cambridge（剑桥大学）；Middle East Technical University（中东技术大学）
Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number of datasets available containing facial images and corresponding expression labels. However, virtually none of these datasets have been acquired with consideration of fair distribution across the human population. Therefore, in this work, we undertake a systematic investigation of bias and fairness in facial expression recognition by comparing three different approaches, namely a baseline, an attribute-aware and a d…
It is well known that deep learning approaches to face recognition and facial landmark detection suffer from biases in modern training datasets. In this work, we propose to use synthetic face images to reduce the negative effects of dataset biases on these tasks. Using a 3D morphable face model, we generate large amounts of synthetic face images with full control over facial shape and color, pose, illumination, and background. With a series of experiments, we extensively test the effects of priming deep nets by pre-training them with synthetic faces. We observe the following positive effects f…
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,…
Published academic research and media articles suggest face recognition is biased across demographics. Specifically, unequal performance is obtained for women, dark-skinned people, and older adults. However, these published studies have examined the bias of facial recognition in the visible spectrum (VIS). Factors such as facial makeup, facial hair, skin color, and illumination variation have been attributed to the bias of this technology at the VIS. The near-infrared (NIR) spectrum offers an advantage over the VIS in terms of robustness to factors such as illumination changes, facial makeup, …
USC Ming Hsieh Department of Electrical and Computer Engineering（南加州大学明谢电气工程与计算机工程系）；USC Information Sciences Institute（南加州大学信息科学研究所）；Visual Intelligence and Multimedia Analytics Laboratory（视觉智能与多媒体分析实验室）
As the social impact of visual recognition has been under scrutiny, several protected-attribute balanced datasets emerged to address dataset bias in imbalanced datasets. However, in facial attribute classification, dataset bias stems from both protected attribute level and facial attribute level, which makes it challenging to construct a multi-attribute-level balanced real dataset. To bridge the gap, we propose an effective pipeline to generate high-quality and sufficient facial images with desired facial attributes and supplement the original dataset to be a balanced dataset at both levels, w…
DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discovery
University of Cambridge（剑桥大学）；Baidu Inc（百度公司）；Central China Normal University（华中师范大学）；La Trobe University（拉筹伯大学）；China University of Geosciences（中国地质大学）；JD Explore Academy（京东探索研究院）
Georgian Partners Inc（Georgian Partners公司）；University of Toronto（多伦多大学）；Toronto Rehabilitation Institute, University Health Network（大学健康网络多伦多康复研究所）；University of Manitoba（曼尼托巴大学）；University of Regina（里贾纳大学）；University of Northern British Columbia（北不列颠哥伦比亚大学）；Vector Institute for Artificial Intelligence（Vector人工智能研究所）
Accurate facial expression analysis is an essential step in various clinical applications that involve physical and mental health assessments of older adults (e.g. diagnosis of pain or depression). Although remarkable progress has been achieved toward developing robust facial landmark detection methods, state-of-the-art methods still face many challenges when encountering uncontrolled environments, different ranges of facial expressions, and different demographics of the population. A recent study has revealed that the health status of individuals can also affect the performance of facial land…
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）
From Bias to Balance: Detecting Facial Expression Recognition Biases in Large Multimodal Foundation Models
Lake Wales High School（莱克威尔士高中）；Thomas Jefferson Sr. High School（托马斯·杰斐逊高中）；Bellarmine College Preparatory（贝拉明学院预科学校）；Algoverse AI Research（Algoverse AI研究机构）
Beijing University of Posts and Telecommunications（北京邮电大学）
Datasets play an important role in the progress of facial expression recognition algorithms, but they may suffer from obvious biases caused by different cultures and collection conditions. To look deeper into this bias, we first conduct comprehensive experiments on dataset recognition and crossdataset generalization tasks, and for the first time explore the intrinsic causes of the dataset discrepancy. The results quantitatively verify that current datasets have a strong buildin bias and corresponding analyses indicate that the conditional probability distributions between source and target dat…
Studies have proven that domain bias and label bias exist in different Facial Expression Recognition (FER) datasets, making it hard to improve the performance of a specific dataset by adding other datasets. For the FER bias issue, recent researches mainly focus on the cross-domain issue with advanced domain adaption algorithms. This paper addresses another problem: how to boost FER performance by leveraging cross-domain datasets. Unlike the coarse and biased expression label, the facial Action Unit (AU) is fine-grained and objective suggested by psychological studies. Motivated by this, we res…
In recent times, there have been increasing accusations on artificial intelligence systems and algorithms of computer vision of possessing implicit biases. Even though these conversations are more prevalent now and systems are improving by performing extensive testing and broadening their horizon, biases still do exist. One such class of systems where bias is said to exist is facial recognition systems, where bias has been observed on the basis of gender, ethnicity, skin tone and other facial attributes. This is even more disturbing, given the fact that these systems are used in practically ev…
Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition
CHI – Chair of Health Informatics, MRI, Technical University of Munich（慕尼黑技术大学健康信息学系）；MCML – Munich Center for Machine Learning（慕尼黑机器学习中心）；GLAM – Group on Language, Audio, & Music（语言、音频与音乐小组）；MDSI – Munich Data Science Institute（慕尼黑数据科学研究所）
University of Cambridge（剑桥大学）；Binghamton University（宾汉姆顿大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
As Facial Expression Recognition (FER) systems become integrated into our daily lives, these systems need to prioritise making fair decisions instead of aiming at higher individual accuracy scores. Ranging from surveillance systems to diagnosing mental and emotional health conditions of individuals, these systems need to balance the accuracy vs fairness trade-off to make decisions that do not unjustly discriminate against specific under-represented demographic groups. Identifying bias as a critical problem in facial analysis systems, different methods have been proposed that aim to mitigate bi…
The presence of bias in deep models leads to unfair outcomes for certain demographic subgroups. Research in bias focuses primarily on facial recognition and attribute prediction with scarce emphasis on face detection. Existing studies consider face detection as binary classification into 'face' and 'non-face' classes. In this work, we investigate possible bias in the domain of face detection through facial region localization which is currently unexplored. Since facial region localization is an essential task for all face recognition pipelines, it is imperative to analyze the presence of such …
Advanced Micro Devices（超威半导体公司）；Lyrebird AI（琴鸟人工智能公司）；Descript（Descript公司）；University of Toronto（多伦多大学）；Li Ka Shing Knowledge Institute（李嘉诚知识研究院）；Princeton University（普林斯顿大学）
In this work, we explore the features that are used by humans and by convolutional neural networks (ConvNets) to classify faces. We use Guided Backpropagation (GB) to visualize the facial features that influence the output of a ConvNet the most when identifying specific individuals; we explore how to best use GB for that purpose. We use a human intelligence task to find out which facial features humans find to be the most important for identifying specific individuals. We explore the differences between the saliency information gathered from humans and from ConvNets. Humans develop biases in e…
Erasmus MC（伊拉斯姆斯大学医学中心）；Delft University of Technology（代尔夫特理工大学）
Confounding bias is a crucial problem when applying machine learning to practice, especially in clinical practice. We consider the problem of learning representations independent to multiple biases. In literature, this is mostly solved by purging the bias information from learned representations. We however expect this strategy to harm the diversity of information in the representation, and thus limiting its prospective usage (e.g., interpretation). Therefore, we propose to mitigate the bias while keeping almost all information in the latent representations, which enables us to observe and int…
Visa Inc.（Visa公司）；Harvard John A. Paulson School Of Engineering And Applied Sciences（哈佛大学约翰·A·保尔森工程与应用科学学院）；FM: Systems（FM: Systems公司）；Autodesk（Autodesk公司）
Gender classification algorithms have important applications in many domains today such as demographic research, law enforcement, as well as human-computer interaction. Recent research showed that algorithms trained on biased benchmark databases could result in algorithmic bias. However, to date, little research has been carried out on gender classification algorithms' bias towards gender minorities subgroups, such as the LGBTQ and the non-binary population, who have distinct characteristics in gender expression. In this paper, we began by conducting surveys on existing benchmark databases for…
Research in social psychology has shown that people's biased, subjective judgments about another's personality based solely on their appearance are not predictive of their actual personality traits. But researchers and companies often utilize computer vision models to predict similarly subjective personality attributes such as "employability." We seek to determine whether state-of-the-art, black box face processing technology can learn human-like appearance biases. With features extracted with FaceNet, a widely used face recognition framework, we train a transfer learning model on human subjec…
