Title
Superpixel based continuous conditional random field neural network for semantic segmentation.
Abstract
•Superpixel based semantic segmentation architecture with three sub- networks.•Inferring CRF on full resolution features.•SP-LAYERs for transforming pixel level features and similarities.•C-CRF-LAYER for implementing continuous conditional randomeld.•A joint pixel and superpixel supervised learning and inference strategy.
Year
DOI
Venue
2019
10.1016/j.neucom.2019.01.016
Neurocomputing
Keywords
Field
DocType
Semantic segmentation,Unary network,Pairwise network,Superpixel based continuous CRF network,Joint learning strategy
Conditional random field,Pairwise comparison,Pattern recognition,Convolutional neural network,Inference,Segmentation,Supervised learning,Artificial intelligence,Artificial neural network,Mathematics,Machine learning,CRFS
Journal
Volume
ISSN
Citations 
340
0925-2312
0
PageRank 
References 
Authors
0.34
30
6
Name
Order
Citations
PageRank
Lei Zhou132.39
Keren Fu229526.25
Zhi Liu379258.22
Fan Zhang422969.82
Zhimin Yin500.34
Jianli Zheng600.34