Open AccessPosted Content
Analysis of Gender Inequality In Face Recognition Accuracy
TLDR
In this paper, the authors present a comprehensive analysis of how and why face recognition accuracy differs between men and women, and they show that accuracy is lower for women due to the combination of the impostor distribution for women having a skew toward higher similarity scores, and the genuine distribution for men having a skewed toward lower similarity scores.Abstract:
We present a comprehensive analysis of how and why face recognition accuracy differs between men and women. We show that accuracy is lower for women due to the combination of (1) the impostor distribution for women having a skew toward higher similarity scores, and (2) the genuine distribution for women having a skew toward lower similarity scores. We show that this phenomenon of the impostor and genuine distributions for women shifting closer towards each other is general across datasets of African-American, Caucasian, and Asian faces. We show that the distribution of facial expressions may differ between male/female, but that the accuracy difference persists for image subsets rated confidently as neutral expression. The accuracy difference also persists for image subsets rated as close to zero pitch angle. Even when removing images with forehead partially occluded by hair/hat, the same impostor/genuine accuracy difference persists. We show that the female genuine distribution improves when only female images without facial cosmetics are used, but that the female impostor distribution also degrades at the same time. Lastly, we show that the accuracy difference persists even if a state-of-the-art deep learning method is trained from scratch using training data explicitly balanced between male and female images and subjects.read more
Citations
More filters
Journal ArticleDOI
Issues Related to Face Recognition Accuracy Varying Based on Race and Skin Tone
TL;DR: Using two different deep convolutional neural network face matchers, it is shown that for a fixed decision threshold, the African-American image cohort has a higher false match rate (FMR), and the Caucasian cohort hasA higher false nonmatch rate.
Journal ArticleDOI
Demographic Bias in Biometrics: A Survey on an Emerging Challenge.
TL;DR: A comprehensive survey of the existing literature on biometric bias estimation and mitigation can be found in this article, where a discussion of the pertinent technical and social matters are discussed as well as the remaining challenges and future work items.
Posted Content
Towards causal benchmarking of bias in face analysis algorithms
TL;DR: An experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change, is developed.
Book ChapterDOI
FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition
TL;DR: The 2020 ChaLearn Looking at People Fair Face Recognition and Analysis Challenge as mentioned in this paper evaluated accuracy and bias in gender and skin colour of submitted algorithms on the task of 1:1 face verification in the presence of other confounding attributes.
Posted Content
How Does Gender Balance In Training Data Affect Face Recognition Accuracy
TL;DR: This work investigates female under-representation in the training data is truly the cause of lower accuracy for females on test data, and shows that gender balance in theTraining data does not translate into gender Balance in the test accuracy, and the “gender gap” in test accuracy is not minimized by a gender-balanced training set, but by a training set with more male images than female images.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
TL;DR: This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead.
Proceedings ArticleDOI
Overview of the face recognition grand challenge
P.J. Phillips,Patrick J. Flynn,T. Scruggs,Kevin W. Bowyer,Jin Chang,K. Hoffman,J. Marques,Jaesik Min,William J. Worek +8 more
TL;DR: The face recognition grand challenge (FRGC) is designed to achieve this performance goal by presenting to researchers a six-experiment challenge problem along with data corpus of 50,000 images.
Proceedings ArticleDOI
VGGFace2: A Dataset for Recognising Faces across Pose and Age
TL;DR: VGGFace2 as discussed by the authors is a large-scale face dataset with 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject.
Proceedings ArticleDOI
SphereFace: Deep Hypersphere Embedding for Face Recognition
TL;DR: In this paper, the angular softmax (A-softmax) loss was proposed to learn angularly discriminative features for deep face recognition under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal interclass distance under a suitably chosen metric space.