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

TL;DR

This paper introduces a Confidence Based Offloading framework for mobile deep learning video analytics, optimizing accuracy and latency by intelligently deciding when to process locally or offload to servers based on confidence scores.

Contribution

It proposes confidence score calibration and an adaptive offloading algorithm to improve DNN accuracy and efficiency on resource-limited mobile devices.

Findings

Significant accuracy improvements over existing methods

Effective offloading decisions based on confidence calibration

Enhanced performance under varying network conditions

Abstract

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.