多视图主动学习的多样性样本选择方法研究

PDF下载HTML

Title:

Diversity sample selection method of multiview active learning classification

作者:

陈立伟, 房赫, 朱海峰

哈尔滨工程大学 信息与通信工程学院, 黑龙江 哈尔滨 150001

Author(s):

CHEN Liwei, FANG He, ZHU Haifeng

College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

关键词:

高光谱图像分类; 多视图主动学习; 多样性; 样本选择; 超像素; 训练样本数量; 预测标签; 分类精度

Keywords:

hyperspectral image classification; multiview active learning; diversity; sample selection; superpixel; number of training samples; prediction labels; accuracy of classification

分类号:

TP753

DOI:

10.11992/tis.202007037

摘要:

为了去除高光谱图像多视图主动学习分类中的所选样本的冗余，降低人工标记成本，本文提出了两种用于多视图主动学习分类中的多样性样本选择方法。将高光谱图像进行超像素分割，将所选样本中属于不同的超像素的样本加入训练集，其余样本加入候选集；比较各视图对样本的预测标签，将所选样本中预测标签不完全相同的样本加入训练集，其余样本加入候选集。本文分别用这两种方法对传统多视图主动学习的样本选择方法进行改进，并用两组高光谱图像数据进行实验。实验结果表明：使用这两种方法改进后，所得分类精度不变，使用的训练样本数量大幅减少。

Abstract:

To remove the redundancy of selected samples in the multiview active learning classification of hyperspectral images and reduce the cost of manual marking, this paper proposes two methods for the selection of diverse samples in the multiview active learning classification. First, hyperspectral images are divided into superpixel segments, then samples belonging to different superpixel segments are added to the training set, and the remaining samples are put back into the candidate set. Second, the prediction labels of the samples from each view are compared, then the samples with different prediction labels are added into the training set, and the remaining samples are put back into the candidate set. In this study, the two methods are used to improve the sample selection method in the traditional multiview active learning classification, and experiments are conducted in two groups of hyperspectral image data. The results show that the accuracy of classification is unchanged, yet the number of training samples is greatly reduced after using the two methods.