Face Recognition Vendor Test (FRVT) - Performance of Automated Gender Classification Algorithms

By Mei Ngan, Patrick Grother. 2015

69 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

In AI Ethics, Fairness & Society

Citations in the corpus

Identifying and Reducing Gender Bias in Word-Level Language Models (2019, background): “The National Institute for Standards and Technology (NIST) evaluated several facial recognition algorithms and found that they are systematically biased based on gender (Ngan and Grother, 2015).”
The Misgendering Machines (2018, methodology): “The literature proposes having an "operator" (presumably some kind of facility security) alerted when this happens [20, 70].”
The What-If Tool: Interactive Probing of Machine Learning Models (2019, methodology): “For example, the NIST gender report [23] evaluates the impact of ethnicity on gender classiﬁcation, using country of origin as a proxy for ethnicity.”
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification (2018, methodology): “The latest gender classiﬁcation report from the National Institute for Standards and Technology (NIST) also shows that algorithms NIST evaluated performed worse for female-labeled faces than male-labeled faces (Ngan et al., 2015).”
Mitigating Bias in Gender, Age and Ethnicity Classification: A Multi-task Convolution Neural Network Approach (2018, background): “The latest report on gender classification released by National Institute for Standards and Technology (NIST) reflects on the fact that algorithms performed worse for females than males [11].”
Gender Recognition or Gender Reductionism?: The Social Implications of Embedded Gender Recognition Systems (2018, background): “user, such that it can better adapt to them [32, 39, 45]; it is also believed to have the ability to enhance surveillance or marketing research by analyzing user data and providing results to marketers [33] or authorities (i.”
Trustworthy Artificial Intelligence: A Review (2022, methodology): “[145] designed the face recognition vendor test FRVT to compare and assess the performance of automated gender classification algorithms.”
Understanding Unequal Gender Classification Accuracy from Face Images (2018, background): “A study by NIST shows that automated gender classiﬁcation algorithms are more accurate for males than females [24].”
How Computers See Gender (2019, background): “Automated facial analysis, and its associated gender classification techniques, have been proposed for a variety of applications, such as access control, real-time security, targeted marketing, and personalized human-robot interaction (e.g. [80, 81, 90, 100]).”
AFIF4: Deep Gender Classification based on AdaBoost-based Fusion of Isolated Facial Features and Foggy Faces (2017, methodology): “The Groups dataset is considered, in the literature, the most challenging and complex dataset for the gender classification problem [32, 33, 34].”
Towards a Standard for Identifying and Managing Bias in Artificial Intelligence (2022, background): “Prepubescent male faces are frequently misclassified as female, and older female faces are progressively misclassified as male [93].”
Actionable Auditing: Investigating the Impact of Publicly Naming Biased Performance Results of Commercial AI Products (2019, methodology): “• Kairos and Amazon perform better onmale faces than female faces, a trend also observed in [9, 29].”