1. A survey: Deep learning for hyperspectral image classification with few labeled samples
- Author
-
Sen Jia, Nanying Li, Shuguo Jiang, Meng Xu, Zhijie Lin, and Shiqi Yu
- Subjects
FOS: Computer and information sciences ,0209 industrial biotechnology ,Source code ,Computer Science - Artificial Intelligence ,Computer science ,Active learning (machine learning) ,Computer Vision and Pattern Recognition (cs.CV) ,Cognitive Neuroscience ,media_common.quotation_subject ,Computer Science - Computer Vision and Pattern Recognition ,02 engineering and technology ,Machine learning ,computer.software_genre ,Field (computer science) ,020901 industrial engineering & automation ,Artificial Intelligence ,FOS: Electrical engineering, electronic engineering, information engineering ,0202 electrical engineering, electronic engineering, information engineering ,Hyperspectral image classification ,media_common ,business.industry ,Deep learning ,Image and Video Processing (eess.IV) ,Hyperspectral imaging ,Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science Applications ,Artificial Intelligence (cs.AI) ,020201 artificial intelligence & image processing ,Artificial intelligence ,Transfer of learning ,Focus (optics) ,business ,computer - Abstract
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 samples 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 labeling. 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 directions. 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 techniques, 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.
- Published
- 2021