TL;DR
MetaAge introduces a meta-learning approach to create personalized age estimators by mapping identity features to age estimator parameters, effectively leveraging large-scale datasets without requiring identity labels or multiple samples per person.
Contribution
The paper proposes MetaAge, a novel meta-learning framework that learns to generate personalized age estimators from identity features, overcoming data limitations of existing methods.
Findings
MetaAge significantly improves age estimation accuracy.
Outperforms state-of-the-art personalized age estimation methods.
Effective on multiple benchmark datasets.
Abstract
Different people age in different ways. Learning a personalized age estimator for each person is a promising direction for age estimation given that it better models the personalization of aging processes. However, most existing personalized methods suffer from the lack of large-scale datasets due to the high-level requirements: identity labels and enough samples for each person to form a long-term aging pattern. In this paper, we aim to learn personalized age estimators without the above requirements and propose a meta-learning method named MetaAge for age estimation. Unlike most existing personalized methods that learn the parameters of a personalized estimator for each person in the training set, our method learns the mapping from identity information to age estimator parameters. Specifically, we introduce a personalized estimator meta-learner, which takes identity features as the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsTest
