Quantization and training of object detection networks with low-precision weights and activations

Bo Yang; Jian Liu; Li Zhou; Yun Wang; Jie Chen

doi:10.1117/1.JEI.27.1.013020

16 February 2018 Quantization and training of object detection networks with low-precision weights and activations

Bo Yang, Jian Liu, Li Zhou, Yun Wang, Jie Chen

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 1, 013020 (February 2018). https://doi.org/10.1117/1.JEI.27.1.013020

Abstract

As convolutional neural networks have demonstrated state-of-the-art performance in object recognition and detection, there is a growing need for deploying these systems on resource-constrained mobile platforms. However, the computational burden and energy consumption of inference for these networks are significantly higher than what most low-power devices can afford. To address these limitations, this paper proposes a method to train object detection networks with low-precision weights and activations. The probability density functions of weights and activations of each layer are first directly estimated using piecewise Gaussian models. Then, the optimal quantization intervals and step sizes for each convolution layer are adaptively determined according to the distribution of weights and activations. As the most computationally expensive convolutions can be replaced by effective fixed point operations, the proposed method can drastically reduce computation complexity and memory footprint. Performing on the tiny you only look once (YOLO) and YOLO architectures, the proposed method achieves comparable accuracy to their 32-bit counterparts. As an illustration, the proposed 4-bit and 8-bit quantized versions of the YOLO model achieve a mean average precision of 62.6% and 63.9%, respectively, on the Pascal visual object classes 2012 test dataset. The mAP of the 32-bit full-precision baseline model is 64.0%.

Citation Download Citation

Bo Yang, Jian Liu, Li Zhou, Yun Wang, and Jie Chen "Quantization and training of object detection networks with low-precision weights and activations," Journal of Electronic Imaging 27(1), 013020 (16 February 2018). https://doi.org/10.1117/1.JEI.27.1.013020

Received: 10 August 2017; Accepted: 23 January 2018; Published: 16 February 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