Quantization of deep convolutional networks

Yea-Shuan Huang; Charles Djimy Slot; Chang Wu Yu

doi:10.1117/12.2549445

27 November 2019 Quantization of deep convolutional networks

Yea-Shuan Huang, Charles Djimy Slot, Chang Wu Yu

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113212R (2019) https://doi.org/10.1117/12.2549445
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

Abstract

In recent years increasingly complex architectures for deep convolutional networks (DCNs) have been proposed to boost the performance on image recognition tasks. However, the gains in performance have come at a cost of substantial increase in computation and model storage resources. Implementation of quantized DCNs has the potential to alleviate some of these complexities and facilitate potential deployment on embedded hardware. In this paper, we experiment with three different quantizers for the implementation of DCNs. We denote them by min-max quantizer (MMQ), average quantizer (AQ) and histogram average quantizer (HAQ). We used a set of 8 different bit-widths (i.e one, two, …, eight bits) to quantize each DCN’s weight to run our experiments. Experimental results show that due to the non-destructive effect on the original distribution of HAQ, it outperforms both MMQ and AQ.

Citation Download Citation

Yea-Shuan Huang, Charles Djimy Slot, and Chang Wu Yu "Quantization of deep convolutional networks", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212R (27 November 2019); https://doi.org/10.1117/12.2549445

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