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...
Main Authors: | Wenxiang Lin, Yan Ding, Hua-Liang Wei, Xinglin Pan, Yutong Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/15/4349 |
Similar Items
-
Hyperspectral Image Classification Network Based on 3D Octave Convolution and Multiscale Depthwise Separable Convolution
by: Qingqing Hong, et al.
Published: (2023-12-01) -
An efficient and accurate deep learning method for tree species classification that integrates depthwise separable convolution and dilated convolution using hyperspectral data
by: Mengni Fu, et al.
Published: (2024-12-01) -
Furniture Image Classification Based on Depthwise Group Over-Parameterized Convolution
by: Han Ye, et al.
Published: (2022-11-01) -
An FPGA-Based CNN Accelerator Integrating Depthwise Separable Convolution
by: Bing Liu, et al.
Published: (2019-03-01) -
Small-Scale Depthwise Separable Convolutional Neural Networks for Bacteria Classification
by: Duc-Tho Mai, et al.
Published: (2021-12-01)