AgeTransGAN for Facial Age Transformation with Rectified Performance Metrics

Abstract

AbstractWe propose the AgeTransGAN for facial age transformation and the improvements to the metrics for performance evaluation. The AgeTransGAN is composed of an encoder-decoder generator and a conditional multitask discriminator with an age classifier embedded. The generator considers cycle-generation consistency, age classification and cross-age identity consistency to disentangle the identity and age characteristics during training. The discriminator fuses age features with the target age group label and collaborates with the embedded age classifier to warrant the desired target age generation. As many previous work use the Face++ APIs as the metrics for performance evaluation, we reveal via experiments the inappropriateness of using the Face++ as the metrics for the face verification and age estimation of juniors. To rectify the Face++ metrics, we made the Cross-Age Face (CAF) dataset which contains 4000 face images of 520 individuals taken from their childhood to seniorhood. The CAF is one of the very few datasets that offer far more images of the same individuals across large age gaps than the popular FG-Net. We use the CAF to rectify the face verification thresholds of the Face++ APIs across different age gaps. We also use the CAF and FFHQ-Aging datasets to compare the age estimation performance of the Face++ APIs and an age estimator that we made, and propose rectified metrics for performance evaluation. We compare the AgeTransGAN with state-of-the-art approaches by using the existing and rectified metrics.