Lee J.-HChan Y.-MChen T.-YCHU-SONG CHEN2021-09-022021-09-022018https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050087068&doi=10.1109%2fMIPR.2018.00036&partnerID=40&md5=221754aced0a31e801338c9971a4afefhttps://scholars.lib.ntu.edu.tw/handle/123456789/581328Automatic 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. ? 2018 IEEE.Convolution; Deep learning; Mobile computing; Mobile devices; Neural networks; Attribute analysis; Computing power; Convolutional Neural Networks (CNN); Gender classification; Joint estimation; Mobile applications; Multitask learning; Neuron networks; Classification (of information)conference paper10.1109/MIPR.2018.000362-s2.0-85050087068