Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning

TL;DR

This paper introduces a new facial hair dataset and a logically consistent prediction loss to improve facial hair attribute classification, revealing its impact on face recognition accuracy across demographics.

Contribution

It presents a new descriptive facial hair annotation scheme, a dataset FH37K, and a novel loss function LCPLoss for enforcing logical consistency in attribute classification.

Findings

Logical consistency improves classification accuracy.

Facial hair influences face recognition performance.

New dataset FH37K enables detailed facial hair analysis.

Abstract

Face attribute research has so far used only simple binary attributes for facial hair; e.g., beard / no beard. We have created a new, more descriptive facial hair annotation scheme and applied it to create a new facial hair attribute dataset, FH37K. Face attribute research also so far has not dealt with logical consistency and completeness. For example, in prior research, an image might be classified as both having no beard and also having a goatee (a type of beard). We show that the test accuracy of previous classification methods on facial hair attribute classification drops significantly if logical consistency of classifications is enforced. We propose a logically consistent prediction loss, LCPLoss, to aid learning of logical consistency across attributes, and also a label compensation training strategy to eliminate the problem of no positive prediction across a set of related attributes. Using an attribute classifier trained on FH37K, we investigate how facial hair affects face recognition accuracy, including variation across demographics. Results show that similarity and difference in facial hairstyle have important effects on the impostor and genuine score distributions in face recognition. The code is at https:// github.com/ HaiyuWu/ LogicalConsistency.