Compressing by Learning in a Low-Rank and Sparse Decomposition Form

Compressing by Learning in a Low-Rank and Sparse Decomposition Form

Low-rankness and sparsity are often used to guide the compression of convolutional neural networks (CNNs) separately. Since they capture global and local structure of a matrix respectively, we combine these two complementary properties together to pursue better network compression performance. Most...

Full description

Bibliographic Details
Main Authors: Kailing Guo, Xiaona Xie, Xiangmin Xu, Xiaofen Xing
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Convolutional neural networks
low-rank
sparse
network compression
Online Access:https://ieeexplore.ieee.org/document/8871134/

Internet

https://ieeexplore.ieee.org/document/8871134/

Similar Items