scholarly journals Multi-Scale Segmentation Method Based on Binary Merge Tree and Class Label Information

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 17801-17816 ◽  
Author(s):  
Tengfei Su ◽  
Shengwei Zhang
Keyword(s):  
Segmentation Method ◽  
Class Label ◽  
Multi Scale ◽  
Label Information

An unsupervised multi-scale segmentation method based on automated parameterization

2016 ◽  
Vol 9 (15) ◽  
Author(s):  
Chao Wang ◽  
Wei Xu ◽  
Xiao-fang Pei ◽  
Xiao-yan Zhou
Keyword(s):  
Segmentation Method ◽  
Multi Scale

scholarly journals An Efficient Parallel Multi-Scale Segmentation Method for Remote Sensing Imagery

2018 ◽  
Vol 10 (4) ◽  
pp. 590 ◽  
Author(s):  
Haiyan Gu ◽  
Yanshun Han ◽  
Yi Yang ◽  
Haitao Li ◽  
Zhengjun Liu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Segmentation Method ◽  
Remote Sensing Imagery ◽  
Multi Scale

scholarly journals Classification and Representation Joint Learning via Deep Networks

2017 ◽  
Author(s):  
Ya Li ◽  
Xinmei Tian ◽  
Xu Shen ◽  
Dacheng Tao
Keyword(s):  
Spatial Distribution ◽  
Deep Learning ◽  
Feature Learning ◽  
Classification Performance ◽  
Local Distribution ◽  
Classification Problems ◽  
Class Label ◽  
Channel Network ◽  
Training Samples ◽  
Label Information

Deep learning has been proven to be effective for classification problems. However, the majority of previous works trained classifiers by considering only class label information and ignoring the local information from the spatial distribution of training samples. In this paper, we propose a deep learning framework that considers both class label information and local spatial distribution information between training samples. A two-channel network with shared weights is used to measure the local distribution. The classification performance can be improved with more detailed information provided by the local distribution, particularly when the training samples are insufficient. Additionally, the class label information can help to learn better feature representations compared with other feature learning methods that use only local distribution information between samples. The local distribution constraint between sample pairs can also be viewed as a regularization of the network, which can efficiently prevent the overfitting problem. Extensive experiments are conducted on several benchmark image classification datasets, and the results demonstrate the effectiveness of our proposed method.

A Variable Multi-Scale Segmentation Method for Spatial Pattern Analysis Using Multispectral WorldView-2 Images

2013 ◽  
Vol 11 (6) ◽  
pp. 1055-1061 ◽  
Author(s):  
Jiajia Liu ◽  
Liangshu Shi ◽  
Chao Zhang ◽  
Jianyu Yang ◽  
Dehai Zhu ◽  
...  
Keyword(s):  
Spatial Pattern ◽  
Pattern Analysis ◽  
Spatial Pattern Analysis ◽  
Segmentation Method ◽  
Multi Scale
Sign in / Sign up

Export Citation Format

Share Document