InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity

TL;DR

InclusiveFaceNet enhances face attribute detection accuracy across diverse demographic groups by learning and leveraging race and gender representations while preserving user privacy, achieving state-of-the-art results.

Contribution

It introduces a method that incorporates demographic information into face attribute detection without compromising privacy, improving accuracy across diverse populations.

Findings

Achieves top performance on Faces of the World and CelebA datasets.

Maintains demographic privacy while improving detection accuracy.

Effectively transfers demographic representations to attribute detection.

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.