Domain-Specific Approximation for Object Detection

Ting Wu Chin, Chia Lin Yu, Matthew Halpern, Hasan Genc, Shiao-Li Tsao, Vijay Janapa Reddi

研究成果: Article同行評審

6 引文 斯高帕斯(Scopus)

摘要

There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection. In this work, we investigate the trade-off between accuracy and speed with domain-specific approximations, i.e. category-aware image size scaling and proposals scaling, for two state-of-the-art deep learning-based object detection meta-architectures. We study the effectiveness of applying approximation both statically and dynamically to understand the potential and the applicability of them. By conducting experiments on the ImageNet VID dataset, we show that domain-specific approximation has great potential to improve the speed of the system without deteriorating the accuracy of object detectors, i.e. up to 7.5x speedup for dynamic domain-specific approximation. To this end, we present our insights toward harvesting domain-specific approximation as well as devise a proof-of-concept runtime, AutoFocus, that exploits dynamic domain-specific approximation.

原文English
頁(從 - 到)31-40
頁數10
期刊IEEE Micro
38
發行號1
DOIs
出版狀態Published - 1 一月 2018

指紋 深入研究「Domain-Specific Approximation for Object Detection」主題。共同形成了獨特的指紋。

引用此