Fair and accurate age prediction using distribution aware data curation and augmentation

TL;DR

This paper proposes novel dataset curation and augmentation methods to improve fairness and diversity in age prediction models, addressing biases related to ethnicity, gender, and age distribution.

Contribution

It introduces distribution-aware data curation and augmentation techniques, including out-of-distribution detection, to enhance fairness and generalization in age prediction systems.

Findings

Outperforms baselines in fairness by up to 4.92 times

Improves generalization over cloud systems by 31.88% and 10.95%

Enhances model fairness and diversity through novel data strategies

Abstract

Deep learning-based facial recognition systems have experienced increased media attention due to exhibiting unfair behavior. Large enterprises, such as IBM, shut down their facial recognition and age prediction systems as a consequence. Age prediction is an especially difficult application with the issue of fairness remaining an open research problem (e.g., predicting age for different ethnicity equally accurate). One of the main causes of unfair behavior in age prediction methods lies in the distribution and diversity of the training data. In this work, we present two novel approaches for dataset curation and data augmentation in order to increase fairness through balanced feature curation and increase diversity through distribution aware augmentation. To achieve this, we introduce out-of-distribution detection to the facial recognition domain which is used to select the data most relevant to the deep neural network's (DNN) task when balancing the data among age, ethnicity, and gender. Our approach shows promising results. Our best-trained DNN model outperformed all academic and industrial baselines in terms of fairness by up to 4.92 times and also enhanced the DNN's ability to generalize outperforming Amazon AWS and Microsoft Azure public cloud systems by 31.88% and 10.95%, respectively.