Hierarchical Attention-Based Age Estimation and Bias Analysis

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 12; pp. 14682 - 14692
• Main Authors: Hiba, Shakediel, Keller, Yosi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-12-2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Age estimation; Aging; Bias; biometrics; Chronology; deep learning; Estimates; Estimation; face analysis; Face recognition; Measurement; Regression models; Statistical analysis; Task analysis; Training; Transformers
• ISSN: 0162-8828; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2023.3319472

In this work, we present a Deep Learning approach to estimate age from facial images. First, we introduce a novel attention-based approach to image augmentation-aggregation, which allows multiple image augmentations to be adaptively aggregated using a Transformer-Encoder. A hierarchical probabilistic regression model is then proposed that combines discrete probabilistic age estimates with an ensemble of regressors. Each regressor is adapted and trained to refine the probability estimate over a given age range. We show that our age estimation scheme outperforms current schemes and provides a new state-of-the-art age estimation accuracy when applied to the MORPH II and CACD datasets. We also present an analysis of the biases in the results of the state-of-the-art age estimates.