Deep feature compression for collaborative object detection
This work addresses efficiency improvements for mobile-cloud collaborative AI applications, presenting an incremental advancement in feature compression techniques.
The paper tackles the problem of communication overhead in collaborative object detection by proposing a strategy for lossy compression of feature data, achieving up to 70% reduction in communication without sacrificing accuracy.
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.