From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning

TL;DR

This paper introduces OrdCon, a contrastive learning framework that models the natural aging process to improve generalized age feature extraction, significantly enhancing cross-dataset performance in age estimation and face recognition.

Contribution

The paper proposes a novel contrastive learning method that explicitly models the ordinal aging process to extract more generalizable age features.

Findings

Achieves comparable results to state-of-the-art in homogeneous datasets.

Reduces mean absolute error by approximately 1.38 in cross-dataset age estimation.

Improves average accuracy for age-invariant face recognition by 1.87%.

Abstract

Generalized age feature extraction is crucial for age-related facial analysis tasks, such as age estimation and age-invariant face recognition (AIFR). Despite the recent successes of models in homogeneous-dataset experiments, their performance drops significantly in cross-dataset evaluations. Most of these models fail to extract generalized age features as they only attempt to map extracted features with training age labels directly without explicitly modeling the natural ordinal progression of aging. In this paper, we propose Order-Enhanced Contrastive Learning (OrdCon), a novel contrastive learning framework designed explicitly for ordinal attributes like age. Specifically, to extract generalized features, OrdCon aligns the direction vector of two features with either the natural aging direction or its reverse to model the ordinal process of aging. To further enhance generalizability, OrdCon leverages a novel soft proxy matching loss as a second contrastive objective, ensuring that features are positioned around the center of each age cluster with minimal intra-class variance and proportionally away from other clusters. By modeling the ageing process, the framework can enhance generalizability by improving the alignment of samples from the same class and reducing the divergence of direction vectors. We demonstrate that our proposed method achieves comparable results to state-of-the-art methods on various benchmark datasets in homogeneous-dataset evaluations for both age estimation and AIFR. In cross-dataset experiments, OrdCon outperforms other methods by reducing the mean absolute error by approximately 1.38 on average for the age estimation task and boosts the average accuracy for AIFR by 1.87%.