One-class remote sensing classification: one-class vs. binary classifiers
One-class remote sensing classification: one-class vs. binary classifiers
复制标题
一类遥感分类：一类分类器与二元分类器
DOI：
10.1080/01431161.2017.1416697
复制
发表时间：
2018-01-01
影响因子：
3.4
通讯作者：
Newsam, Shawn
中科院分区：
文献类型：
--
作者：
Deng, Xueqing;Li, Wenkai;Newsam, Shawn
遥感的许多应用只需要对单一的土地类型进行分类。这被称为单类分类问题，它可以使用二进制分类器，通过将所有其他类视为负类，或只考虑感兴趣的类的单类分类器来执行。这两种方法之间的关键区别在于它们的训练数据和产生它所需的工作量。二进制分类器需要一个穷举标记的训练数据集，而一类分类器只使用感兴趣的类的样本进行训练。在充分和完整的训练数据下，二进制分类器通常优于单类分类器。然而，不清楚的是，当给定相同数量的标记训练数据时，哪种方法更准确。也就是说，对于固定的标签工作，使用二进制分类器还是单类分类器更好。这是我们在这篇文章中考虑的问题。我们比较了几个二进制分类器，包括反向传播神经网络，支持向量机，最大似然分类器，两个一类分类器，一类SVM，存在和背景学习（PBL），在高分辨率遥感图像的一类分类问题。我们表明，给定一个固定的标签预算，PBL始终优于其他方法。这一优势源于PBL是一种阳性未标记方法，其中大量容易获得的未标记数据被纳入训练阶段，允许分类器更有效地对阴性类进行建模。
ABSTRACT Many applications of remote sensing only require the classification of a single land type. This is known as the one-class classification problem and it can be performed using either binary classifiers, by treating all other classes as the negative class, or one-class classifiers which only consider the class of interest. The key difference between these two approaches is in their training data and the amount of effort needed to produce it. Binary classifiers require an exhaustively labelled training data set while one-class classifiers are trained using samples of just the class of interest. Given ample and complete training data, binary classifiers generally outperform one-class classifiers. However, what is not clear is which approach is more accurate when given the same amount of labelled training data. That is, for a fixed labelling effort, is it better to use a binary or one-class classifier. This is the question we consider in this article. We compare several binary classifiers, including backpropagation neural networks, support vector machines, and maximum likelihood classifiers, with two one-class classifiers, one-class SVM, and presence and background learning (PBL), on the problem of one-class classification in high-resolution remote sensing imagery. We show that, given a fixed labelling budget, PBL consistently outperforms the other methods. This advantage stems from the fact that PBL is a positive-unlabelled method in which large amounts of readily available unlabelled data is incorporated into the training phase, allowing the classifier to model the negative class more effectively.