Age Classification Using Convolutional Neural Networks with the Multi-class Focal Loss

3rd International Conference on Automation, Control and Robotics Engineering

工业技术;计算机科学;无线电电子学

Liu, Wei^1 ; Chen, Lin^2 ; Chen, Yajun^3

School of Computer Science and Technology, China West Normal University, No.1, Shida Road, Shunqing District, Nanchong, China^1

Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, No. 266 Fangzheng Avenue, Beibei District, Chongqing, China^2

Education and Information Technology Center, China West Normal University, No.1, Shida Road, Shunqing District, Nanchong, China^3

关键词: Age classification;    Class imbalance;    Convolutional neural network;    Cross entropy;    Data collection;    Experimental analysis;    Facial images;    Loss functions;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/428/1/012043/pdf
DOI  :  10.1088/1757-899X/428/1/012043

来源: IOP

【 摘 要 】

Automatic age classification has drawn significant interest in plenty of applications such as access control, human-computer interaction, law enforcement and surveillance. Automatic age classification is a challenging task due to the complexity of facial images. A large number of approaches have been investigated on unconstrained datasets. However, most of these approaches have focused on the network architecture rather than the distribution of data, i.e., the extreme class imbalance existing among different age groups as the difficulty of data collection. In this paper, we propose a convolutional neural networks model based on the multi-class focal loss function. Specifically, our approach is designed to address the class imbalance via reshaping the standard cross entropy loss that it down-weights the loss assigned to well-classified examples. We validate our approach on well-known Adience benchmark. Finally, the experimental analysis shows that the proposed model achieves a significant improvement in performance for age classification.