Frequency Regularization: Reducing Information Redundancy in Convolutional Neural Networks

Convolutional neural networks have demonstrated impressive results in many computer vision tasks. However, the increasing size of these networks raises concerns about the information overload resulting from the large number of network parameters. In this paper, we propose Frequency Regularization to...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Chenqiu Zhao, Guanfang Dong, Shupei Zhang, Zijie Tan, Anup Basu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2023-01-01
coleção:	IEEE Access
Assuntos:	Frequency domain information redundancy network regularization convolutional neural network
Acesso em linha:	https://ieeexplore.ieee.org/document/10266314/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!