Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children

TL;DR

This paper introduces the Inter-Prototype loss, a novel approach that enhances face recognition between children and adults by reducing inter-child similarity, leading to improved accuracy without extra data or parameters.

Contribution

The paper proposes a new loss function that decreases similarity among children's images, improving child-adult face recognition without additional data or learnable parameters.

Findings

Outperforms existing baselines in child-adult face recognition

Does not require extra child images or additional training parameters

Effective in distinguishing children in face recognition tasks

Abstract

Despite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adult images belong to the same identity. Previous approaches mainly focused on increasing the similarity between child and adult images of a given identity to overcome the discrepancy of facial appearances due to aging. However, we observe that reducing the similarity between child images of different identities is crucial for learning distinct features among children and thus improving face recognition performance in child-adult pairs. Based on this intuition, we propose a novel loss function called the Inter-Prototype loss which minimizes the similarity between child images. Unlike the previous studies, the Inter-Prototype loss does not require additional child images or training additional learnable parameters. Our extensive experiments and in-depth analyses show that our approach outperforms existing baselines in face recognition with child-adult pairs. Our code and newly-constructed test sets of child-adult pairs are available at https://github.com/leebebeto/Inter-Prototype.