Cross-Age Contrastive Learning for Age-Invariant Face Recognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Haoyi, Sanchez, Victor, Li, Chang-Tsun
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917557973286912
author Wang, Haoyi
Sanchez, Victor
Li, Chang-Tsun
author_facet Wang, Haoyi
Sanchez, Victor
Li, Chang-Tsun
contents Cross-age facial images are typically challenging and expensive to collect, making noise-free age-oriented datasets relatively small compared to widely-used large-scale facial datasets. Additionally, in real scenarios, images of the same subject at different ages are usually hard or even impossible to obtain. Both of these factors lead to a lack of supervised data, which limits the versatility of supervised methods for age-invariant face recognition, a critical task in applications such as security and biometrics. To address this issue, we propose a novel semi-supervised learning approach named Cross-Age Contrastive Learning (CACon). Thanks to the identity-preserving power of recent face synthesis models, CACon introduces a new contrastive learning method that leverages an additional synthesized sample from the input image. We also propose a new loss function in association with CACon to perform contrastive learning on a triplet of samples. We demonstrate that our method not only achieves state-of-the-art performance in homogeneous-dataset experiments on several age-invariant face recognition benchmarks but also outperforms other methods by a large margin in cross-dataset experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2312_11195
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Cross-Age Contrastive Learning for Age-Invariant Face Recognition
Wang, Haoyi
Sanchez, Victor
Li, Chang-Tsun
Computer Vision and Pattern Recognition
Cross-age facial images are typically challenging and expensive to collect, making noise-free age-oriented datasets relatively small compared to widely-used large-scale facial datasets. Additionally, in real scenarios, images of the same subject at different ages are usually hard or even impossible to obtain. Both of these factors lead to a lack of supervised data, which limits the versatility of supervised methods for age-invariant face recognition, a critical task in applications such as security and biometrics. To address this issue, we propose a novel semi-supervised learning approach named Cross-Age Contrastive Learning (CACon). Thanks to the identity-preserving power of recent face synthesis models, CACon introduces a new contrastive learning method that leverages an additional synthesized sample from the input image. We also propose a new loss function in association with CACon to perform contrastive learning on a triplet of samples. We demonstrate that our method not only achieves state-of-the-art performance in homogeneous-dataset experiments on several age-invariant face recognition benchmarks but also outperforms other methods by a large margin in cross-dataset experiments.
title Cross-Age Contrastive Learning for Age-Invariant Face Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.11195