Cross-Age Contrastive Learning for Age-Invariant Face Recognition

TL;DR

This paper introduces a semi-supervised contrastive learning method called CACon that leverages face synthesis to improve age-invariant face recognition, achieving state-of-the-art results especially in cross-dataset scenarios.

Contribution

The paper proposes a novel semi-supervised contrastive learning approach using synthesized face images to enhance age-invariant face recognition performance.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Outperforms existing methods significantly in cross-dataset tests.

Effectively leverages synthesized samples for contrastive learning.

Abstract

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.