Convolutional Neural Networks (CNNs) have been proven very effective for human demographics estimation by a number of recent studies. However, the proposed solutions significantly vary in different aspects leaving many open questions on how to choose an optimal CNN architecture and which training strategy to use. In this work, we shed light on some of these questions improving the existing CNN-based approaches for gender and age prediction and providing practical hints for future studies. In particular, we analyse four important factors of the CNN training for gender recognition and age estimation: (1) the target age encoding and loss function, (2) the CNN depth, (3) the need for pretraining, and (4) the training strategy: mono-task or multi-task. As a result, we design the state-of-the-art gender recognition and age estimation models according to three popular benchmarks: LFW, MORPH-II and FG-NET. Moreover, our best model won the ChaLearn Apparent Age Estimation Challenge 2016 significantly outperforming the solutions of other participants.
Effective training of convolutional neural networks for face-based gender and age prediction
Pattern Recognition, Volume 72, December 2017
© Elsevier. Personal use of this material is permitted. The definitive version of this paper was published in Pattern Recognition, Volume 72, December 2017 and is available at : https://doi.org/10.1016/j.patcog.2017.06.031
PERMALINK : https://www.eurecom.fr/publication/5252