Multi-Lane Capsule Network for Classifying Images With Complex Background

Multi-Lane Capsule Network for Classifying Images With Complex Background

Capsule Network (CapsNet) is a novel structure for deep neural network, mapping the region of target instance to vectors and matrices rather than scalars. This process is enabled by dynamic routing algorithm which help CapsNet to achieve more robust capacity with fewer parameters than traditional CN...

Full description

Bibliographic Details
Main Authors: Siwei Chang, Jin Liu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Capsule network
multi-lane
strict-squash
drop-circuit
lane-filter
complex background
Online Access:https://ieeexplore.ieee.org/document/9079546/

Internet

https://ieeexplore.ieee.org/document/9079546/

Similar Items