Authors:
Chuan Kai Wang
and
Long Wen Chang
Affiliation:
Department of Computer Science, National Tsing Hua University and Republic of China
Keyword(s):
Semantic Segmentation, Convolutional Neural Network, Global Convolutional Network, DenseNet, Concatenation, ResNet, FC-DenseNet, and CamVid.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Cardiovascular Imaging and Cardiography
;
Cardiovascular Technologies
;
Health Engineering and Technology Applications
;
Pattern Recognition
;
Signal Processing
;
Software Engineering
Abstract:
Most of the segmentation CNNs (convolutional neural network) based on the ResNet. Recently, Huang et al. introduced a new classification CNN called DenseNet. Then Jégou et al. used a sequence of building blocks for DenseNet to build their semantic segmentation CNN, called FC-DenseNet, and achieved state-of-the-art results on CamVid dataset. In this paper, we implement the design concept of DenseNet into a ResNet-based semantic segmentation CNN called Global Convolutional Network (GCN) and build our own network by switching every identity mapping operation of the decoder network in GCN to a concatenation operation. Our network uses less computational resources than FC-DenseNet to obtain a mean IoU score of 69.34% on CamVid dataset, and surpass the 66.9% obtained in the paper of FC-DenseNet.