Group binary weight networks

Kailing Guo; Yicai Yang; Xiaofen Xing; Xiangmin Xu

doi:10.1117/12.2540888

31 July 2019 Group binary weight networks

Kailing Guo, Yicai Yang, Xiaofen Xing, Xiangmin Xu

Proceedings Volume 11198, Fourth International Workshop on Pattern Recognition; 1119812 (2019) https://doi.org/10.1117/12.2540888
Event: Fourth International Workshop on Pattern Recognition, 2019, Nanjing, China

Abstract

In recent years, quantizing the weights of a deep neural network draws increasing attention in the area of network compression. An efficient and popular way to quantize the weight parameters is to replace a filter with the product of binary values and a real-valued scaling factor. However, the quantization error of such binarization method raises as the number of a filter's parameter increases. To reduce quantization error in existing network binarization methods, we propose group binary weight networks (GBWN), which divides the channels of each filter into groups and every channel in the same group shares the same scaling factor. We binarize the popular network architectures VGG, ResNet and DesneNet, and verify the performance on CIFAR10, CIFAR100, Fashion-MNIST, SVHN and ImageNet datasets. Experiment results show that GBWN achieves considerable accuracy increment compared to recent network binarization methods, including BinaryConnect, Binary Weight Networks and Stochastic Quantization Binary Weight Networks.

Citation Download Citation

Kailing Guo, Yicai Yang, Xiaofen Xing, and Xiangmin Xu "Group binary weight networks", Proc. SPIE 11198, Fourth International Workshop on Pattern Recognition, 1119812 (31 July 2019); https://doi.org/10.1117/12.2540888

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Binary data

Quantization

Network architectures

Convolution

Neural networks

Algorithm development

Convolutional neural networks

RELATED CONTENT

Method for training a compact discrete neural network descriptor
Proceedings of SPIE (March 04 2022)

Neural network quantization algorithms based on weights and activation values
Proceedings of SPIE (May 06 2022)

Fast recognition of cat and dog images based on network...
Proceedings of SPIE (December 08 2022)

Quantification of lung abnormalities in cystic fibrosis using deep networks
Proceedings of SPIE (March 02 2018)

Identifying disease free chest x ray images with deep transfer...
Proceedings of SPIE (March 13 2019)

Bipolar morphological neural networks: convolution without multiplication
Proceedings of SPIE (January 31 2020)

Customization and optimization of SSD based neural network model for...
Proceedings of SPIE (July 31 2019)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years