期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 49, 期 2, 页码 717-725出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2010.2058578
关键词
Biased support-vector machine (SVM) (BSVM); Gaussian domain descriptor (GDD); land cover; one-class classification; one-class SVM (OCSVM); positive and unlabeled learning (PUL); remote sensing
类别
资金
- National Science Foundation [BDI 0742986]
- UC/National Lab
- Direct For Biological Sciences [0742986] Funding Source: National Science Foundation
- Div Of Biological Infrastructure [0742986] Funding Source: National Science Foundation
In remote-sensing classification, there are situations when users are only interested in classifying one specific land-cover type, without considering other classes. These situations are referred to as one-class classification. Traditional supervised learning is inefficient for one-class classification because it requires all classes that occur in the image to be exhaustively assigned labels. In this paper, we investigate a new positive and unlabeled learning (PUL) algorithm, applying it to one-class classifications of two scenes of a high-spatial-resolution aerial photograph. The PUL algorithm trains a classifier on positive and unlabeled data, estimates the probability that a positive training sample has been labeled, and generates binary predictions for test samples using an adjusted threshold. Experimental results indicate that the new algorithm provides high classification accuracy, outperforming the biased support-vector machine (SVM), one-class SVM, and Gaussian domain descriptor methods. The advantages of the new algorithm are that it can use unlabeled data to help build classifiers, and it requires only a small set of positive data to be labeled by hand. Therefore, it can significantly reduce the effort of assigning labels to training data without losing predictive accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据