A survey: Deep learning for hyperspectral image classification with few labeled samples
A survey: Deep learning for hyperspectral image classification with few labeled samples
复制标题
一项调查：利用少量标记样本进行高光谱图像分类的深度学习
DOI：
10.1016/j.neucom.2021.03.035
复制
发表时间：
2021-04-16
期刊：
影响因子：
6
通讯作者：
Yu, Shiqi
中科院分区：
文献类型：
--
作者：
Jia, Sen;Jiang, Shuguo;Yu, Shiqi
随着深度学习技术的快速发展和计算能力的提高，深度学习在高光谱图像分类领域得到了广泛的应用。一般而言，深度学习模型通常包含许多可训练参数，并且需要大量的标记样本才能达到最优性能。然而，在HSI分类方面，由于人工标记的困难和耗时的性质，通常很难获得大量的标记样本。因此，许多研究工作都集中在利用较少的标记样本构建HSI分类的深度学习模型。在本文中，我们专注于这一主题，并对相关文献进行了系统的回顾。具体地说，本文的贡献是双重的。首先，根据学习范式对相关方法的研究进展进行了分类，包括迁移学习、主动学习和少镜头学习。其次，用各种最先进的方法进行了大量的实验，并对结果进行了总结，以揭示潜在的研究方向。更重要的是，值得注意的是，尽管深度学习模型(通常需要足够的标记样本)与少标记样本的HSI场景之间存在巨大差距，但小样本集问题可以很好地融合深度学习方法和相关技术，如迁移学习和轻量级模型。关于重现性，论文中评估的方法的源代码可以在https://github.com/ShuGuoJ/HSI-Classification.git.上找到(C)2021年提交人(S)。Elsevier B.V.出版。这是一篇基于CC by License(http://creativecommons.org/licenses/by/4.0/).的开放获取文章
With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled sam-ples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual label-ing. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research direc-tions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related tech-niques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://github.com/ShuGuoJ/HSI-Classification.git. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).