Deep feature compression for collaborative object detection

TL;DR

This paper investigates the impact of lossy feature data compression on collaborative object detection accuracy and proposes a strategy to reduce communication overhead by up to 70% without accuracy loss.

Contribution

It introduces a novel approach for lossy feature compression in collaborative object detection and a strategy to maintain accuracy while significantly reducing data transmission.

Findings

Communication overhead reduced by up to 70%.

Lossy compression can be effectively used without accuracy loss.

Proposed strategy improves efficiency in collaborative object detection.

Abstract

Recent studies have shown that the efficiency of deep neural networks in mobile applications can be significantly improved by distributing the computational workload between the mobile device and the cloud. This paradigm, termed collaborative intelligence, involves communicating feature data between the mobile and the cloud. The efficiency of such approach can be further improved by lossy compression of feature data, which has not been examined to date. In this work we focus on collaborative object detection and study the impact of both near-lossless and lossy compression of feature data on its accuracy. We also propose a strategy for improving the accuracy under lossy feature compression. Experiments indicate that using this strategy, the communication overhead can be reduced by up to 70% without sacrificing accuracy.