{Xilin Chen Shiguang Shan Hu Han Wenxian Liu Shuzhe Wu Jie Zhang Meina Kan Shaoxin Li Xin Liu}

Abstract

Apparent age estimation from face image has attractedmore and more attentions as it is favorable in some realworld applications. In this work, we propose an end-toend learning approach for robust apparent age estimation,named by us AgeNet. Specifically, we address the apparent age estimation problem by fusing two kinds of models,i.e., real-value based regression models and Gaussian label distribution based classification models. For both kindof models, large-scale deep convolutional neural network isadopted to learn informative age representations. Anotherkey feature of the proposed AgeNet is that, to avoid the problem of over-fitting on small apparent age training set, we exploit a general-to-specific transfer learning scheme. Technically, the AgeNet is first pre-trained on a large-scale webcollected face dataset with identity label, and then it is finetuned on a large-scale real age dataset with noisy age label.Finally, it is fine-tuned on a small training set with apparent age label. The experimental results on the ChaLearn2015 Apparent Age Competition demonstrate that our AgeNet achieves the state-of-the-art performance in apparentage estimation.