InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity

2017/12/01 by Hee Jung Ryu, Hartwig Adam, Ryu, Hee Jung +3 · 7 citations
Computer Science · Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Evolutionary Psychology and Human Behavior #FOS: Computer and information sciences #Face recognition and analysis #Law in Society and Culture

paper · pdf · doi:10.48550/arxiv.1712.00193

openalex publication_date 2017/12/01 · openalex created_date 2018/07/10 · openalex updated_date 2026/07/28

Abstract

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 while resulting in some of the best reported numbers to date on attribute detection in the Faces of the World and CelebA datasets.

Citations

• Equality of Opportunity in Supervised Learning
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations

Cited by

• Understanding Unequal Gender Classification Accuracy from Face Images
• Robustness Disparities in Commercial Face Detection
• On the effect of age perception biases for real age regression
• FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age
• Harnessing Geometric Constraints from Emotion Labels to improve Face Verification
• 50 Years of Test (Un)fairness
• Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Related

• Jointly De-biasing Face Recognition and Demographic Attribute Estimation
• SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning
• FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age
• Exploring Vision Language Models for Facial Attribute Recognition: Emotion, Race, Gender, and Age
• Multi-Task Faces (MTF) Data Set: A Legally and Ethically Compliant Collection of Face Images for Various Classification Tasks