An Improved Capsule Network Based on Capsule Filter Routing
Capsule network (CapsNet) is a novel type of network that can retain spatial information, because each capsule can integrate more information than scalar-output features. However, the CapsNet learns all the features in the input image due to the lack of pooling operation, and there is no connection...
Main Authors: | Wei Wang, Feifei Lee, Shuai Yang, Qiu Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9505676/ |
Similar Items
-
Capsule Network Improved Multi-Head Attention for Word Sense Disambiguation
by: Jinfeng Cheng, et al.
Published: (2021-03-01) -
Residual Vector Capsule: Improving Capsule by Pose Attention
by: Ning Xie, et al.
Published: (2021-01-01) -
RS-CapsNet: An Advanced Capsule Network
by: Shuai Yang, et al.
Published: (2020-01-01) -
Separable Attention Capsule Network for Signal Classification
by: Shaoqing Liu, et al.
Published: (2020-01-01) -
Multi-channel capsule network ensemble for plant disease detection
by: Musa Peker
Published: (2021-06-01)