Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images

Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images

Semantic image segmentation has recently witnessed considerable progress by training deep convolutional neural networks (CNNs). The core issue of this technique is the limited capacity of CNNs to depict visual objects. Existing approaches tend to utilize approximate inference in a discrete domain or...

Full description

Bibliographic Details
Main Authors: Mi Zhang, Xiangyun Hu, Like Zhao, Ye Lv, Min Luo, Shiyan Pang
Format: Article
Language:English
Published: MDPI AG 2017-05-01
Series:Remote Sensing
Subjects:
semantic segmentation
deep convolutional neural networks
manifold ranking
single stream optimization
high resolution image
Online Access:http://www.mdpi.com/2072-4292/9/5/500

Internet

http://www.mdpi.com/2072-4292/9/5/500

Similar Items