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

2025-01-03

AI Summary

Existing age estimation and age-invariant face recognition models exhibit weak generalization across datasets, primarily because they fail to model the inherent orderliness of human biological aging and the evolutionary规律 of facial features. To address this, we propose Ordinal Contrastive Learning (OrdCon), the first method to explicitly align deep feature directions with the biological aging process. OrdCon introduces a soft proxy matching loss to reduce intra-class variance and enhance inter-class discriminability. Additionally, we design an age-cluster centroid optimization mechanism that jointly enforces contrastive learning, metric learning, and directional alignment constraints. Extensive cross-dataset evaluations on multiple benchmarks demonstrate that OrdCon reduces mean absolute error in age estimation by 1.38 years and improves accuracy in age-invariant face recognition by 1.87%, achieving state-of-the-art performance.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Local Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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 progression of aging. In this paper, we propose Order-Enhanced Contrastive Learning (OrdCon), which aims to extract generalized age features to minimize the domain gap across different datasets and scenarios. OrdCon aligns the direction vector of two features with either the natural aging direction or its reverse to effectively model the aging process. The method also leverages metric learning which is incorporated with a novel soft proxy matching loss to ensure that features are positioned around the center of each age cluster with minimum intra-class variance. 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, our method reduces the mean absolute error by about 1.38 in average for age estimation task and boosts the average accuracy for AIFR by 1.87%.

Problem

• Cross-dataset Age Recognition
• Complexity of Human Aging
• Consistent Age Feature Extraction

Innovation

• OrdCon
• age-invariant features
• cross-age recognition