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

arXiv: https://arxiv.org/abs/2501.01760 · HTML: https://mlsanity.com/paper/2501.01760/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 99 references that are in the map.
- First posted on arXiv 3 Jan 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Arc2Face: A Foundation Model for ID-Consistent Human Faces](https://mlsanity.com/paper/2403.11641/) (2024)
- [Towards the Generalization of Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2111.00743/) (2021)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [Level Playing Field for Million Scale Face Recognition](https://mlsanity.com/paper/1705.00393/) (2017)
- [Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach](https://mlsanity.com/paper/1706.00906/) (2017)
- [BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation](https://mlsanity.com/paper/1904.03358/) (2019)
- [Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology](https://mlsanity.com/paper/2112.14656/) (2021)
- [When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework](https://mlsanity.com/paper/2103.01520/) (2021)
- [Masked Contrastive Graph Representation Learning for Age Estimation](https://mlsanity.com/paper/2306.17798/) (2023)
- [Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression](https://mlsanity.com/paper/2204.00309/) (2022)
- [Decorrelated Adversarial Learning for Age-Invariant Face Recognition](https://mlsanity.com/paper/1904.04972/) (2019)
- [Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition](https://mlsanity.com/paper/1809.00338/) (2018)
- [Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition](https://mlsanity.com/paper/1810.07599/) (2018)
- [A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark](https://mlsanity.com/paper/2307.04570/) (2023)
- [Deep Differentiable Random Forests for Age Estimation](https://mlsanity.com/paper/1907.10665/) (2019)
- [Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation](https://mlsanity.com/paper/2210.15878/) (2022)
- [Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion](https://mlsanity.com/paper/2112.10167/) (2021)

## Built on by (most cited first, 4 of 4)

- [Underage Detection through a Multi-Task and MultiAge Approach for Screening Minors in Unconstrained Imagery](https://mlsanity.com/paper/2506.10689/) (2025)
- [Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation](https://mlsanity.com/paper/2511.00123/) (2025)
- [Coordinative Learning with Ordinal and Relational Priors for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2511.11276/) (2025)
- [The Good, the Better, and the Best: Improving the Discriminability of Face Embeddings through Attribute-aware Learning](https://mlsanity.com/paper/2603.15062/) (2026)

## Abstract (arXiv)

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%.