SKASNet: Lightweight Convolutional Neural Network for Semantic Segmentation

Most of existing semantic segmentation models apply receptive fields of a single size in each convolution layer,which deters the models from extracting multi-scale features.To address the problem,this paper implements selective kernel convolution to build a novel residual module,Selective-Kernel-Arr...

Full description

Bibliographic Details
Published in:Jisuanji gongcheng
Main Author: TAN Lei, SUN Huaijiang
Format: Article
Language:English
Published: Editorial Office of Computer Engineering 2020-09-01
Subjects:
convolutional neural network(cnn)|semantic segmentation|selective kernel convolution|layer-wise grouped convolution|lightweight network model
Online Access:https://www.ecice06.com/fileup/1000-3428/PDF/20200936.pdf

Internet

https://www.ecice06.com/fileup/1000-3428/PDF/20200936.pdf

Similar Items