Orange Labsteam: Grigory Antipov1,2, Moez Baccouche1, Sid-Ahmed Berrani1, Jean-Luc Dugelay2
This work describes our solution in the second edition of the ChaLearn LAP competition on Apparent Age Estimation . Starting from a pretrained version of the VGG-16 convolutional neural network (CNN) for face recognition, we train it on the huge IMDB-Wiki dataset for biological age estimation and then fine-tune it for apparent age estimation using the relatively small competition dataset. We show that the precise age estimation of children is the cornerstone of the competition. Therefore, we integrate a separate
children VGG-16 network for apparent age estimation of children between 0 and 12 years old in our final solution. The
children network is fine-tuned from the
general one. We employ different age encoding strategies for training
children networks: the soft one (label distribution encoding) for the
general network and the strict one (0/1 classification encoding) for the
children network. Finally, we highlight the importance of the state-of-the-art face detection and face alignment for the final apparent age estimation. Our resulting solution wins the 1st place in the competition significantly outperforming the runner-up.
Our solution is inspired by the solution of the winners  of the first edition of the ChaLearn LAP competition on Apparent Age Estimation. We also use the
Head Hunter algorithm  for face detection and the VGG-16 CNN architecture  for age estimation. Following , we firstly train VGG-16 CNNs for biological age estimation on the IMDB-Wiki dataset and then fine-tune them for apparent age estimation using the competition data.
We further improve the previous year's solution  by proposing the following novelties:
generalmodel and 0/1 classification encoding for the
 S. Escalera, M. Torres, B. Martinez, X. Baro, H. J. Escalante et al.,
 M. Mathias, R. Benenson, M. Pedersoli, L. Van Gool.
 K. Simonyan, A. Zisserman.
 X. Geng, C. Yin, Z. Zhou.
 M. Uricar, V. Franc, D. Thomas, A. Sugimoto and V. Hlavac.