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

by   Tianxiang Tan, et al.

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.


page 1

page 2

page 3

page 4


FastVA: Deep Learning Video Analytics Through Edge Processing and NPU in Mobile

Many mobile applications have been developed to apply deep learning for ...

Calibration-Aided Edge Inference Offloading via Adaptive Model Partitioning of Deep Neural Networks

Mobile devices can offload deep neural network (DNN)-based inference to ...

Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource

Deep Neural Networks (DNNs) have significantly improved the accuracy of ...

Echo: An Edge-Centric Code Offloading System with Quality of Service Guarantee

Code offloading is promising to accelerate mobile applications and save ...

Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks

The edge computing paradigm places compute-capable devices - edge server...

DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation

Deep learning has shown impressive performance in semantic segmentation,...

Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning

Recent breakthroughs in deep learning (DL) have led to the emergence of ...

Please sign up or login with your details

Forgot password? Click here to reset