Out-of-distribution detection and generalization to enhance fairness in age prediction.

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 distribution aware curation and increase diversity through distribution aware augmentation. To achieve this, we created an out-of-distribution technique 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. When it comes to generalization, the increase in diversity also enhanced the DNN's performance, outperforming state-of-the-art approaches of prior research on the Age Estimation Benchmark dataset AFAD by 30.40% and the Amazon AWS and Microsoft Azure public cloud systems by 31.88% and 10.95%, respectively.