Deep Learning on Mobile Devices Through Neural Processing Units and Edge Computing

Deep Neural Network (DNN) is becoming adopted for video analytics on mobile devices. To reduce the delay of running DNNs, many mobile devices are equipped with Neural Processing Units (NPU). However, due to the resource limitations of NPU, these DNNs have to be compressed to increase the processing speed at the cost of accuracy. To address the low accuracy problem, we propose a Confidence Based Offloading (CBO) framework for deep learning video analytics. The major challenge is to determine when to return the NPU classification result based on the confidence level of running the DNN, and when to offload the video frames to the server for further processing to increase the accuracy. We first identify the problem of using existing confidence scores to make offloading decisions, and propose confidence score calibration techniques to improve the performance. Then, we formulate the CBO problem where the goal is to maximize accuracy under some time constraint, and propose an adaptive solution that determines which frames to offload at what resolution based on the confidence score and the network condition. Through real implementations and extensive evaluations, we demonstrate that the proposed solution can significantly outperform other approaches.

I. Introduction

Deep Neural Networks (DNN) have been successfully applied to various computer vision and natural language processing problems. Recently, many applications based on DNNs have been developed to provide more intelligent video analytics. For example, some drones such as DJI Mavic Pro can recognize and follow a target based on video analytics; law enforcement officers can use smart glasses to identify suspects [1]. In these applications, only lightweight DNNs can be run locally and their accuracy is much lower than advanced DNNs. Although advanced DNNs can provide us with better results, they also suffer from high computational overhead which means long delay and more energy consumption when running on mobile devices.