A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples

TL;DR

This survey reviews deep learning methods for hyperspectral image classification when labeled samples are scarce, categorizing approaches by learning paradigm and analyzing experimental results to identify future research directions.

Contribution

It systematically categorizes recent methods based on transfer, active, and few-shot learning, and provides experimental insights into their effectiveness for limited labeled data scenarios.

Findings

Fusion of deep learning with transfer and lightweight models addresses small-sample challenges.

State-of-the-art approaches show promising results in limited labeled sample scenarios.

Experimental analysis reveals potential research directions for future work.

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.