Hierarchical Multi-View Semi-Supervised Learning for Very High-Resolution Remote Sensing Image Classification
Hierarchical Multi-View Semi-Supervised Learning for Very High-Resolution Remote Sensing Image Classification
复制标题
用于超高分辨率遥感图像分类的分层多视图半监督学习
DOI：
10.3390/rs12061012
复制
发表时间：
2020
期刊：
影响因子：
5
通讯作者：
Irfana Bibi
中科院分区：
文献类型：
--
作者：
Cheng Shi;Zhiyong Lv;Xiuhong Yang;Pengfei Xu;Irfana Bibi
传统的甚高分辨率遥感图像分类方法需要大量的标记样本才能获得较高的分类精度。有标签的样品很难获得，而且价格昂贵。因此，半监督学习成为一种有效的模式，结合标记和未标记的样本进行分类。在半监督学习中，关键问题是通过选择高可靠性的未标记样本来扩大训练集。从多个视图观察样本有助于提高未标记样本的标签预测精度。因此，合理的视图划分对于提高分类性能至关重要。本文提出了一种基于神经网络的分层多视图半监督学习框架（HMVSSL），用于VHR遥感图像分类。首先，提出了一种基于超像素的样本放大方法，以增加每个视图中的训练样本数量。其次，设计了一种视图划分方法，将训练集划分为两个独立的视图，划分后的子集具有内部紧凑性和内部区别性。最后，提出了一种协同分类策略，用于最终分类。在三幅VHR遥感图像上进行了实验，实验结果表明，该方法优于现有的几种方法。
Traditional classification methods used for very high-resolution (VHR) remote sensing images require a large number of labeled samples to obtain higher classification accuracy. Labeled samples are difficult to obtain and costly. Therefore, semi-supervised learning becomes an effective paradigm that combines the labeled and unlabeled samples for classification. In semi-supervised learning, the key issue is to enlarge the training set by selecting highly-reliable unlabeled samples. Observing the samples from multiple views is helpful to improving the accuracy of label prediction for unlabeled samples. Hence, the reasonable view partition is very important for improving the classification performance. In this paper, a hierarchical multi-view semi-supervised learning framework with CNNs (HMVSSL) is proposed for VHR remote sensing image classification. Firstly, a superpixel-based sample enlargement method is proposed to increase the number of training samples in each view. Secondly, a view partition method is designed to partition the training set into two independent views, and the partitioned subsets are characterized by being inter-distinctive and intra-compact. Finally, a collaborative classification strategy is proposed for the final classification. Experiments are conducted on three VHR remote sensing images, and the results show that the proposed method performs better than several state-of-the-art methods.