Dense Convolutional Networks for Semantic Segmentation

Dense Convolutional Networks for Semantic Segmentation

Recent studies have greatly promoted the development of semantic segmentation. Most state-of-the-art methods adopt fully convolutional networks (FCNs) to accomplish this task, in which the fully connected layer is replaced with the convolution layer for dense prediction. However, standard convolutio...

Full description

Bibliographic Details
Main Authors: Chaoyi Han, Yiping Duan, Xiaoming Tao, Jianhua Lu
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Dense convolution unit
fully convolutional network
overlapped prediction
semantic segmentation
Online Access:https://ieeexplore.ieee.org/document/8678765/

Internet

https://ieeexplore.ieee.org/document/8678765/

Similar Items