Venue
- NeurIPS 2022
Date
- 2022
Share
A View From Somewhere: Human-Centric Face Representations
Jerone T. A. Andrews
Przemyslaw Joniak*
* External authors
NeurIPS 2022
2022
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.
Related Publications
This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. While…
Biases in large-scale image datasets are known to influence the performance of computer vision models as a function of geographic context. To investigate the limitations of standard Internet data collection methods in low- and middle-income countries, we analyze human-centri…
Human-centric image datasets are critical to the development of computer vision technologies. However, recent investigations have foregrounded significant ethical issues related to privacy and bias, which have resulted in the complete retraction, or modification, of several …
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
