Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications
Computer Vision and Pattern Recognition
2018-06-07 v1
Abstract
Automatic age and gender classification based on unconstrained images has become essential techniques on mobile devices. With limited computing power, how to develop a robust system becomes a challenging task. In this paper, we present an efficient convolutional neural network (CNN) called lightweight multi-task CNN for simultaneous age and gender classification. Lightweight multi-task CNN uses depthwise separable convolution to reduce the model size and save the inference time. On the public challenging Adience dataset, the accuracy of age and gender classification is better than baseline multi-task CNN methods.
Keywords
Cite
@article{arxiv.1806.02023,
title = {Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications},
author = {Jia-Hong Lee and Yi-Ming Chan and Ting-Yen Chen and Chu-Song Chen},
journal= {arXiv preprint arXiv:1806.02023},
year = {2018}
}
Comments
To publish in the IEEE first International Conference on Multimedia Information Processing and Retrieval, 2018. (IEEE MIPR 2018)