Kernel Quantization for Efficient Network Compression

Kernel Quantization for Efficient Network Compression

This paper presents a novel network compression framework, <bold>Kernel Quantization</bold> (<bold><italic>KQ</italic></bold>), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version wi...

Full description

Bibliographic Details
Main Authors: Zhongzhi Yu, Yemin Shi
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Kernel quantization
network compression
convolutional neural network
low-precision
low-bit
Online Access:https://ieeexplore.ieee.org/document/9672186/

Internet

https://ieeexplore.ieee.org/document/9672186/

Similar Items