A survey: Deep learning for hyperspectral image classification with few labeled samples

Jia，Sen1,3; Jiang，Shuguo1; Lin，Zhijie1; Li，Nanying1; Xu，Meng1,3; Yu，Shiqi2

2021-08-11

10.1016/j.neucom.2021.03.035

NEUROCOMPUTING   影响因子和分区

0925-2312

1872-8286

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/).

Hyperspectral image classification Deep learning Transfer learning Few-shot learning

SCI ; EI

英语

ESI高被引

通讯

National Natural Science Foundation of China[41971300,61901278,61976144] ; National Key Research and Development Program of China[2020AAA0140002] ; Program for Young Changjiang Scholars, the Key Project of Department of Education of Guangdong Province[2020ZDZX3045] ; Shenzhen Scientific Research and Development Funding Program["JCYJ20180305124802421","JCYJ20180305125902403"]

Computer Science

Computer Science, Artificial Intelligence

WOS:000652811900016

ELSEVIER

20211610237252

Deep learning ; Hyperspectral imaging ; Spectroscopy

Ergonomics and Human Factors Engineering:461.4 ; Data Processing and Image Processing:723.2 ; Imaging Techniques:746

COMPUTER SCIENCE

Web of Science

1.College of Computer Science and Software Engineering,Shenzhen University,China
2.Department of Computer Science and Engineering,Southern University of Science and Technology,China
3.SZU Branch,Shenzhen Institute of Artificial Intelligence and Robotics for Society,China

Jia，Sen,Jiang，Shuguo,Lin，Zhijie,et al. A survey: Deep learning for hyperspectral image classification with few labeled samples[J]. NEUROCOMPUTING,2021,448:179-204.

Jia，Sen,Jiang，Shuguo,Lin，Zhijie,Li，Nanying,Xu，Meng,&Yu，Shiqi.(2021).A survey: Deep learning for hyperspectral image classification with few labeled samples.NEUROCOMPUTING,448,179-204.

Jia，Sen,et al."A survey: Deep learning for hyperspectral image classification with few labeled samples".NEUROCOMPUTING 448(2021):179-204.