Transfer of Learning in the Convolutional Neural Networks on Classifying Geometric Shapes Based on Local or Global Invariants

Transfer of Learning in the Convolutional Neural Networks on Classifying Geometric Shapes Based on Local or Global Invariants

The convolutional neural networks (CNNs) are a powerful tool of image classification that has been widely adopted in applications of automated scene segmentation and identification. However, the mechanisms underlying CNN image classification remain to be elucidated. In this study, we developed a new...

Full description

Bibliographic Details
Main Authors: Yufeng Zheng, Jun Huang, Tianwen Chen, Yang Ou, Wu Zhou
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-02-01
Series:Frontiers in Computational Neuroscience
Subjects:
ShapeNet
topological perception
convolutional neural network (CNN)
global feature
shape classification
Online Access:https://www.frontiersin.org/articles/10.3389/fncom.2021.637144/full

Internet

https://www.frontiersin.org/articles/10.3389/fncom.2021.637144/full

Similar Items