Feature Compression for Rate Constrained Object Detection on the Edge

04/15/2022
by   Zhongzheng Yuan, et al.
3

Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual analytics neural networks. An emerging approach to solve this problem is to offload the computation of these neural networks to computing resources at an edge server. Efficient computation offloading requires optimizing the trade-off between multiple objectives including compressed data rate, analytics performance, and computation speed. In this work, we consider a "split computation" system to offload a part of the computation of the YOLO object detection model. We propose a learnable feature compression approach to compress the intermediate YOLO features with light-weight computation. We train the feature compression and decompression module together with the YOLO model to optimize the object detection accuracy under a rate constraint. Compared to baseline methods that apply either standard image compression or learned image compression at the mobile and perform image decompression and YOLO at the edge, the proposed system achieves higher detection accuracy at the low to medium rate range. Furthermore, the proposed system requires substantially lower computation time on the mobile device with CPU only.

READ FULL TEXT
research
08/21/2021

Supervised Compression for Resource-constrained Edge Computing Systems

There has been much interest in deploying deep learning algorithms on lo...
research
02/12/2018

Deep feature compression for collaborative object detection

Recent studies have shown that the efficiency of deep neural networks in...
research
07/21/2020

Accelerating Deep Learning Applications in Space

Computing at the edge offers intriguing possibilities for the developmen...
research
10/30/2017

High efficiency compression for object detection

Image and video compression has traditionally been tailored to human vis...
research
11/17/2020

The Role of Edge Robotics As-a-Service in Monitoring COVID-19 Infection

Deep learning technology has been widely used in edge computing. However...
research
11/11/2019

A Computing Kernel for Network Binarization on PyTorch

Deep Neural Networks have now achieved state-of-the-art results in a wid...
research
11/10/2021

Towards Live Video Analytics with On-Drone Deeper-yet-Compatible Compression

In this work, we present DCC(Deeper-yet-Compatible Compression), one ena...

Please sign up or login with your details

Forgot password? Click here to reset