Scalable Feature Compression for Edge-Assisted Object Detection Over Time-Varying Networks

Zhongzheng Yuan, Siddharth Garg, Elza Erkip, Yao Wang

Keywords: feature compression, edge computing, object detection

TL;DR: We propose a scalable compression approach for compressing the intermediate feature of object detection model for split-computing applications.

Abstract: Split-computing has recently emerged as a paradigm for offloading computation of visual analytics models from low-powered mobile devices to edge or cloud servers, by which the mobiles execute part of the model and compress and send the intermediate features, and the servers complete the remaining model computation. Prior feature compression approaches train different compression models and possibly visual analytics models to reach different target bit rates. We propose a scalable compression model that compresses the intermediate features of the YOLO object detection model into a layered bitstream, which can be easily adapted to meet the rate constraint of a dynamic network. Our approach achieves comparable rate-accuracy performance compared to prior non-scalable compression approaches over a large bitrate range.