Share Email Print
cover

Proceedings Paper

Exploring the two-stage approach in neural network compression for object detection
Author(s): Xiao Meng; Lixin Yu D.D.S.; Zhiyong Qin D.D.S.
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Recently, convolutional neural network (CNN) has been widely implemented in the compute vision, nature language processing and automatic driving. However, it makes much difficulties to employ the neural network in the embedded system because of the limit of memory storage and the computation bandwidth. To address those limitations, we explore a two-stage approach in neural network compression for the scene, object detection. In this paper, we first propose an effective pruning approach on a trained neural network, and achieve total 81.86%-91.54% sparse rate with the accuracy losing 1-3%. Then we explore the quantization method to apply on the pruned neural network, and propose an adaptive codebook to store the quantized weight parameters and the index of the weight parameters. We utilize the two-stage model compression approach, model pruning and weights quantization, to implement on tiny-YOLO, the state-of-art object detection model, achieving total 41.9-62.7X compression rate with the accuracy loss less than 3.3%.

Paper Details

Date Published: 15 March 2019
PDF: 7 pages
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110411W (15 March 2019); doi: 10.1117/12.2522911
Show Author Affiliations
Xiao Meng, Beijing Microelectronics Technology Institute (China)
Lixin Yu D.D.S., Beijing Microelectronics Technology Institute (China)
Zhiyong Qin D.D.S., Beijing Microelectronics Technology Institute (China)


Published in SPIE Proceedings Vol. 11041:
Eleventh International Conference on Machine Vision (ICMV 2018)
Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray