Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image Classification
Recent research in deep Convolutional Neural Networks(CNN) faces the challenges of vanishing/exploding gradient issues, training instability, and feature redundancy. Orthogonality Regularization(OR), which introduces a penalty function considering the orthogonality of neural networks, could be a rem...
Main Authors: | Taehyeon Kim, Se-Young Yun |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9804718/ |
Similar Items
-
FocusedDropout for Convolutional Neural Network
by: Minghui Liu, et al.
Published: (2022-07-01) -
Structured Pruning of Convolutional Neural Networks via L1 Regularization
by: Chen Yang, et al.
Published: (2019-01-01) -
Convolutional Neural Network-Based Natural Image and MRI Classification Using Gaussian Activated Parametric (GAP) Layer
by: Bijen Khagi, et al.
Published: (2021-01-01) -
Feature Mining: A Novel Training Strategy for Convolutional Neural Network
by: Tianshu Xie, et al.
Published: (2022-03-01) -
Regularized CNN Feature Hierarchy for Hyperspectral Image Classification
by: Muhammad Ahmad, et al.
Published: (2021-06-01)