Few-Shot Personalized Age Estimation
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors point out that people age differently, so treating every face the same way for age guessing isn't ideal. They propose using pictures of the same person taken at different ages to personalize age estimates. To do this, they created OpenPAE, a new open benchmark to test methods that use several reference images per person. Their tests show that personalizing age estimates helps and that more complex models work better than simpler ones. They also share all their tools publicly for others to use.
age estimationpersonalizationbenchmark datasetN-shot learningBayesian linear regressionneural processesdomain adaptationface recognitionmachine learning
Authors
Jakub Paplhám, Vojtěch Franc, Artem Moroz
Abstract
Existing age estimation methods treat each face as an independent sample, learning a global mapping from appearance to age. This ignores a well-documented phenomenon: individuals age at different rates due to genetics, lifestyle, and health, making the mapping from face to age identity-dependent. When reference images of the same person with known ages are available, we can exploit this context to personalize the estimate. The only existing benchmark for this task (NIST FRVT) is closed-source and limited to a single reference image. In this work, we introduce OpenPAE, the first open benchmark for $N$-shot personalized age estimation with strict evaluation protocols. We establish a hierarchy of increasingly sophisticated baselines: from arithmetic offset, through closed-form Bayesian linear regression, to a conditional attentive neural process. Our experiments show that personalization consistently improves performance, that the gains are not merely domain adaptation, and that nonlinear methods significantly outperform simpler alternatives. We release all models, code, protocols, and evaluation splits.