MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
This addresses the need for lightweight deep learning models for mobile vision applications, enabling practical deployment under resource constraints.
The paper tackles the problem of deploying convolutional neural networks on mobile and embedded devices by introducing MobileNets, a class of efficient models based on depth-wise separable convolutions, achieving strong performance on ImageNet classification with trade-offs between latency and accuracy.
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. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.