Relative Age Estimation Using Face Images

2025-02-07

AI Summary

This paper addresses the limited accuracy and systematic bias in single-image face relative age estimation. We propose an iterative optimization framework based on differential regression. Our method models age differences relative to visually similar faces from a reference gallery, enabling robust comparative age reasoning. Key contributions include: (1) the first differential regression paradigm for relative age estimation; (2) an error-distribution-aware iterative age refinement strategy that dynamically corrects initial predictions; and (3) an interpretable bias analysis framework that systematically identifies bias sources across age distribution, gender, and race—revealing previously uncharacterized disparities in mainstream models. Evaluated on MORPH II and CACD, our approach achieves state-of-the-art performance, significantly outperforming absolute age estimation baselines. Results demonstrate that relative modeling substantially improves both robustness and fairness in age estimation.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

This work introduces a novel deep-learning approach for estimating age from a single facial image by refining an initial age estimate. The refinement leverages a reference face database of individuals with similar ages and appearances. We employ a network that estimates age differences between an input image and reference images with known ages, thus refining the initial estimate. Our method explicitly models age-dependent facial variations using differential regression, yielding improved accuracy compared to conventional absolute age estimation. Additionally, we introduce an age augmentation scheme that iteratively refines initial age estimates by modeling their error distribution during training. This iterative approach further enhances the initial estimates. Our approach surpasses existing methods, achieving state-of-the-art accuracy on the MORPH II and CACD datasets. Furthermore, we examine the biases inherent in contemporary state-of-the-art age estimation techniques.

Problem

• Refine age estimation from facial images
• Leverage reference database for accuracy
• Model age-dependent facial variations effectively

Innovation

• Deep-learning age estimation refinement
• Differential regression for facial variations
• Iterative age augmentation scheme