A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices

Authors

  • Yuxuan Cai Northeastern University
  • Geng Yuan Northeastern University
  • Hongjia Li Northeastern University
  • Wei Niu College of William and Mary
  • Yanyu Li Northeastern University
  • Xulong Tang University of Pittsburgh
  • Bin Ren College of William and Mary
  • Yanzhi Wang Northeastern University

Keywords:

Object Detection, Real-time Detection On Mobile Devices, Model Compression, Compression-Compilation Co-Design

Abstract

The rapid development and wide utilization of object detection techniques have aroused requirements for both accuracy and speed of object detectors. In this work, we propose a compression-compilation co-design framework to achieve real-time YOLOv4 inference on mobile devices. We propose a novel fine-grained structured pruning, which maintain high accuracy while achieving high hardware parallelism. Our pruned YOLOv4 achieves 48.9 mAP and 17 FPS inference speed on an off-the-shelf Samsung Galaxy S20 smartphone, which is 5.5x faster than the original state-of-the-art detector YOLOv4.

Downloads

Published

2021-05-18

How to Cite

Cai, Y., Yuan, G., Li, H., Niu, W., Li, Y., Tang, X., Ren, B., & Wang, Y. (2021). A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15997-16000. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17992