Iterative Training Sampling Coupled With Active Learning for Semisupervised Spectral–Spatial Hyperspectral Image Classification
Iterative Training Sampling Coupled With Active Learning for Semisupervised Spectral–Spatial Hyperspectral Image Classification
复制标题
DOI：
10.1109/tgrs.2021.3053204
复制
发表时间：
2021-02
影响因子：
8.2
通讯作者：
K. Ma;Chein-I. Chang
中科院分区：
文献类型：
--
作者：
K. Ma;Chein-I. Chang
训练样本选择对于高光谱图像分类（HSIC）来说是一个巨大的挑战，特别是当只有非常有限的标记数据样本可用于训练时。最近开发的两个用于训练样本选择的概念特别令人感兴趣。一种是主动学习（AL），它通过将未标记的数据样本作为新的训练样本来增强标记的训练样本。另一种是迭代训练采样（ITS），它通过将额外的空间分类信息包含到训练样本中来扩展数据立方体。本文同时结合 AL 和 ITS，得出一种联合 ITS-AL 谱空间（SS）分类方法，称为 AL 谱空间分类的 ITS 增强，简称 ITSA-AL-SS，它可以单独使用 AL 或 ITS 来改进 SS 分类。 ITSA-AL-SS的新颖思想是利用ITS来扩展数据立方体，通过将额外的空间分类信息迭代地合并到AL增强的未标记数据样本中，以在一次性操作中迭代更新当前训练样本。正如预期的那样，ITSA-AL-SS 受益于 ITS 和 AL，不仅进一步提高了分类精度，而且减少了分类不一致。
Training sample selection is a great challenge for hyperspectral image classification (HSIC), specifically when only a very limited number of labeled data samples are available for training. Two recently developed concepts for training sample selection are of particular interest. One is active learning (AL), which augments labeled training samples by including unlabeled data samples as new training samples. The other is iterative training sampling (ITS), which expands data cubes by including additional spatial classification information into the training samples. This article combines AL and ITS simultaneously to derive a joint ITS–AL spectral–spatial (SS) classification approach, to be called ITS augmentation by AL spectral–spatial classification, referred to as ITSA-AL-SS, which can improve SS classification using either AL or ITS alone. The novel idea of ITSA-AL-SS is to take advantage of ITS to expand data cubes by incorporating additional spatial classification information iteratively into the AL-augmented unlabeled data samples to update the current training samples iteration by iteration in one-shot operation. As expected, ITSA-AL-SS is benefited from both ITS and AL to not only further improve classification accuracy but also reduce classification inconsistency.