Hierarchical Attention-based Age Estimation and Bias Estimation
This work addresses age estimation for applications like security or demographics, but it appears incremental as it builds on existing deep learning and attention mechanisms without a major paradigm shift.
The authors tackled age estimation from face images by proposing a hierarchical attention-based deep learning method that combines dual image augmentation-aggregation with a probabilistic regression framework, achieving state-of-the-art accuracy on the MORPH II dataset.
In this work we propose a novel deep-learning approach for age estimation based on face images. We first introduce a dual image augmentation-aggregation approach based on attention. This allows the network to jointly utilize multiple face image augmentations whose embeddings are aggregated by a Transformer-Encoder. The resulting aggregated embedding is shown to better encode the face image attributes. We then propose a probabilistic hierarchical regression framework that combines a discrete probabilistic estimate of age labels, with a corresponding ensemble of regressors. Each regressor is particularly adapted and trained to refine the probabilistic estimate over a range of ages. Our scheme is shown to outperform contemporary schemes and provide a new state-of-the-art age estimation accuracy, when applied to the MORPH II dataset for age estimation. Last, we introduce a bias analysis of state-of-the-art age estimation results.