MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

17 Apr 2017Andrew G. Howard • Menglong Zhu • Bo Chen • Dmitry Kalenichenko • Weijun Wang • Tobias Weyand • Marco Andreetto • Hartwig Adam

We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Image Classification ImageNet MobileNet-224 Top 1 Accuracy 70.6% # 14
Image Classification ImageNet MobileNet-224 Top 5 Accuracy 89.5% # 14