Paper Info
Title
The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon.
Abstract
In this paper, we study the use of unlabeled samples in reducing the problem of small training sample size that can severely affect the recognition rate of classifiers when the dimensionality of the multispectral data is high. We show that by using additional unlabeled samples that are available at no extra cost, the performance may be improved, and therefore the Hughes phenomenon can be mitigated. Furthermore, by experiments, we show that by using additional unlabeled samples more representative estimates can be obtained. We also propose a semiparametric method for incorporating the training (i.e., labeled) and unlabeled samples simultaneously into the parameter estimation process.
Year
DOI
Venue
1994
10.1109/36.312897
IEEE T. Geoscience and Remote Sensing
Keywords
Field
DocType
feature extraction,geophysical techniques,geophysics computing,image recognition,remote sensing,Hughes phenomenon,additional unlabeled samples,classifier,dimensionality,feature extraction,geophysical technique measurement,image classification,image processing,land surface imaging,multispectral remote sensing,parameter estimation,parametric method,pattern recognition,recognition rate,semiparametric method,small sample size problem,small training sample size,terrain mapping optical visible infrared IR,training,unlabeled samples
Computer vision,Computer science,Remote sensing,Curse of dimensionality,Feature extraction,Multispectral pattern recognition,Artificial intelligence,Estimation theory,Contextual image classification,Classifier (linguistics),Sample size determination,Multispectral data
Journal
Volume
Issue
ISSN
32
5
0196-2892
Citations 
PageRank 
References 
166
31.34
5
Authors
2
Search Limit
100166
Name
Order
Citations
PageRank
Behzad M. Shahshahani116631.34
David A. Landgrebe2807125.38