LdsConv: Learned Depthwise Separable Convolutions by Group Pruning

Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning...

Descripción completa

Detalles Bibliográficos
Autores principales: Lin, Wenxiang, Ding, Yan, Wei, Hua-Liang, Pan, Xinglin, Zhang, Yutong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7435949/
https://www.ncbi.nlm.nih.gov/pubmed/32759800
http://dx.doi.org/10.3390/s20154349

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7435949/
https://www.ncbi.nlm.nih.gov/pubmed/32759800
http://dx.doi.org/10.3390/s20154349

Ejemplares similares