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

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-theart 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.

Recent Advances in Multi- and Hyperspectral Image Analysis

“…Importantly, generating ground-truth image data containing manually-delineated objects of interest is not only user-dependent and error-prone, but also cumbersome and costly, as it requires transferring raw image data for further analysis; e.g., from an imaging satellite or other remote imagers [15]. This issue negatively affects our ability to train well-performing supervised learners for HSI analysis that could benefit from large training samples [16,17]. Additionally, the thorough and fair validation of developed approaches is challenging, as their generalization abilities must be investigated with care in order not to infer overoptimistic (or over-pessimistic) conclusions about their performance [18].…”

Regularized CNN Feature Hierarchy for Hyperspectral Image Classification

“…In the last few years, deep learning, especially Convolutional Neural Networks (CNNs), has received widespread attention due to its ability to automatically learn nonlinear features for classification, i.e., overcome the challenges of hand-crafted features for HSIC using traditional methods [16] such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest, Ensemble Learning, Artificial Neural Network, and Extreme Learning Machine (ELM) [17,18]. Moreover, CNN can jointly investigate the spatial-spectral information and such models can be categorized into two groups, i.e., single and two-stream; more information regarding single or two-stream methods can be found in [19]. This work explicitly investigates a single-stream method similar to the works proposed by Ahmad et al [20] (A Fast and Compact 3D CNN for HSIC), Xie et al [21] (Hyperspectral Face Recognition-based on Sparse Spectral Attention Deep Neural Network), Liu et al [22] (A semi-supervised CNN for HSIC), Hamida et al [23] (3D Deep Learning Approach for Remote Sensing Image Classification), Lee et al [24] (Contextual Deep CNN-based HSIC), Chen et al [25] (Contextual Deep CNN-based HSIC), Li [26] (Spectral-Spatial Classification of HSI with 3D CNN), He et al [27] (Multi-scale 3D Deep CNN Network for HSI), Zhao et al [28] (Hybrid Depth-Separable Residual Networks for HSIC).…”

A Framework of Structural Damage Detection for Civil Structures Using Fast Fourier Transform and Deep Convolutional Neural Networks

“…With the development of sensors technology and data acquisition, SHM systems can collect an amount of data from various sensors installed on civil structures. Since deep learning methods effectively handle massive data, it has attracted much attention from many researchers in many fields such as image classification [14,15] and natural language processing [16]. In these methods, vibration-based convolutional neural networks (CNN) algorithms are widely utilized in civil engineering since it is powerful in extracting the feature from raw vibration data to recognize structural damage.…”