Training accurate and compact one-stage object detection networks with heuristic knowledge

Jiyuan Jia; Li Zhou; Jian Liu; Jie Chen

doi:10.1117/1.JEI.27.6.063003

15 November 2018 Training accurate and compact one-stage object detection networks with heuristic knowledge

Jiyuan Jia, Li Zhou, Jian Liu, Jie Chen

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 6, 063003 (November 2018). https://doi.org/10.1117/1.JEI.27.6.063003

Abstract

A training scheme called region-refocusing (RR) is proposed to improve the accuracy and accelerate the convergence of compact one-stage detection neural networks. Main contributions are as follows: (1) the RR mask is first proposed to incorporate the position information and the significance of objects, whereby the regions containing objects can be learned selectively by the compact student detector, which leads to more reasonable feature expressions; (2) within the RR training framework, the selected objectness features from the large teacher detector are utilized to enrich the supervision information and enhance the loss functions for training the student detector, which eventually contributes to rapid convergence and accurate detection; (3) by virtue of the RR scheme, the mean average precision (mAP) of the compact detector can be significantly improved even if the model is initialized from scratch. Superiority of RR has been verified on several benchmark data sets in comparison with other training schemes; the mAP of the well-known tiny-YOLOv2 can be improved from 57.4% to 63.8% by 6.4 points on the VOC2007 test set when the weights are pretrained on ImageNet. Remarkably, when the pretraining process is omitted, it yields a significant boost of mAP by 22.6 points compared with plain training scheme, which demonstrates the robustness and high efficiency of the RR training scheme. Meanwhile, the compact one-stage detector trained with our framework is competent to be deployed on resource-constrained devices for the competitive precision as well as having a lower requirement for computing power.

Citation Download Citation

Jiyuan Jia, Li Zhou, Jian Liu, and Jie Chen "Training accurate and compact one-stage object detection networks with heuristic knowledge," Journal of Electronic Imaging 27(6), 063003 (15 November 2018). https://doi.org/10.1117/1.JEI.27.6.063003

Received: 27 June 2018; Accepted: 24 October 2018; Published: 15 November 2018

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available