A Comparison of Human and Machine Learning Errors in Face Recognition

TL;DR

This paper introduces the elsarticle.cls LaTeX document class, designed to format submissions for Elsevier journals while minimizing package conflicts by building on article.cls and leveraging standard packages such as natbib, geometry, and hyperref. It contrasts elsarticle.cls with the older elsart.cls, highlighting improvements like a more robust design, default preprint formatting, and better support for theorem environments and citation management. The manuscript provides practical guidance on obtaining, generating, and installing the class (via CTAN and the author resources page) and explains the available formatting options to accommodate different journal models. Overall, the work standardizes and streamlines the document preparation process for Elsevier submissions, enabling consistent formatting across models (preprint, final, two-column) and easier integration with common TeX toolchains.

Abstract

Machine learning applications in high-stakes scenarios should always operate under human oversight. Developing an optimal combination of human and machine intelligence requires an understanding of their complementarities, particularly regarding the similarities and differences in the way they make mistakes. We perform extensive experiments in the area of face recognition and compare two automated face recognition systems against human annotators through a demographically balanced user study. Our research uncovers important ways in which machine learning errors and human errors differ from each other, and suggests potential strategies in which human-machine collaboration can improve accuracy in face recognition.