A View From Somewhere: Human-Centric Face Representations

Jerone Theodore Alexander Andrews, Przemyslaw Joniak, Alice Xiang

Keywords: similarity, faces, annotator bias, computer vision, cognitive, mental representations, diversity

TL;DR: Implicit discovery of face-varying dimensions and annotator bias by learning on a novel face similarity dataset

Abstract: We propose to implicitly learn a set of continuous face-varying dimensions, without ever asking an annotator to explicitly categorize a person. We uncover the dimensions by learning on a novel dataset of 638,180 human judgments of face similarity (FAX). We demonstrate the utility of our learned embedding space for predicting face similarity judgments, collecting continuous face attribute values, and attribute classification. Moreover, using a novel conditional framework, we show that an annotator's demographics influences the importance they place on different attributes when judging similarity, underscoring the need for diverse annotator groups to avoid biases.

Community Implementations: [ 5 code implementations](https://www.catalyzex.com/paper/arxiv:2303.17176/code)