With limited number of labeled samples, hyperspectral image (HSI) classification is a difficult Problem in current research. The graph neural network (GNN) has emerged as an approach to semi-supervised classification, and the application GNN images attracted much attention. However, existing GNN-based methods single or filter mainly used extract HSI features, which does not take full advantage various networks (graph filters). Moreover, traditional GNNs have problem oversmoothing. To...

Due to prior knowledge deficiency, large spectral variability, and high dimension of hyperspectral image (HSI), HSI clustering is extremally a fundamental but challenging task. Deep methods have achieved remarkable success attracted increasing attention in unsupervised classification (HSIC). However, the poor robustness, adaptability, feature presentation limit their practical applications complex large-scale datasets. Thus, this article introduces novel self-supervised locality preserving...

Hyperspectral image (HSI) clustering is a challenging task due to the high complexity of HSI data. Subspace has been proven be powerful for exploiting intrinsic relationship between data points. Despite impressive performance in clustering, traditional subspace methods often ignore inherent structural information among In this paper, we revisit with graph convolution and present novel framework called Graph Convolutional Clustering (GCSC) robust clustering. Specifically, recasts...

The joint clustering of multimodal remote sensing (RS) data poses a critical and challenging task in Earth observation. Although recent advances multiview subspace have shown remarkable success, existing methods become computationally prohibitive when dealing with large-scale RS datasets. Moreover, they neglect intrinsic nonlinear spatial interdependencies among heterogeneous lack generalization ability for out-of-sample data, thereby restricting their applicability. This article introduces...

Self-supervised hyperspectral image (HSI) clustering remains a fundamental yet challenging task due to the absence of labeled data and inherent complexity spatial-spectral interactions. While recent advancements have explored innovative approaches, existing methods face critical limitations in accuracy, feature discriminability, computational efficiency, robustness noise, hindering their practical deployment. In this paper, self-supervised efficient low-pass contrastive graph (SLCGC) is...

Hyperspectral image (HSI) consists of hundreds continuous narrow bands with high redundancy, resulting in the curse dimensionality and an increased computation complexity HSI classification. Many clustering-based band selection approaches have been proposed to deal such a problem. However, few them consider spectral spatial relationship simultaneously. In this letter, we novel approach using deep subspace clustering (DSC). The combines task into convolutional autoencoder by treating it as...

Currently, deep neural networks (DNNs) are an important method for handling hyperspectral image (HSI) classification because of their good performance in processing. However, DNNs' depends on a massive number training data and hyperparameters that carefully fine-tuned, which results structural complexity time-consuming process. Deep forest is novel learning does not need much has simple structure. In this paper, we first design spectral-based HSI then propose improved algorithm, named...

Deep subspace clustering has achieved remarkable performances in the unsupervised classification of hyperspectral images. However, previous models based on pixel-level self-expressiveness data suffer from exponential growth computational complexity and access memory requirements with increasing number samples, thus leading to poor applicability large This paper presents a Neighborhood Contrastive Subspace Clustering network (NCSC), scalable robust deep approach, for Instead using...

Hyperspectral images (HSIs) consist of hundreds continuous bands with high correlation, making it contain great abundant information. Band selection is an effective idea for removing redundant and preserving the physical significance at same time. Popular sparse representation-based band commonly introduces additional coefficient to combine error term constraint term, difficult find out optimal balance coefficient. In this letter, we propose a hybrid clustering-based band-selection approach...

Hyperspectral image (HSI) consists of hundreds continuous narrow bands with high spectral correlation, which would lead to the so-called Hughes phenomenon and computational cost in processing. Band selection has been proven effective avoiding such problems by removing redundant bands. However, many existing band methods separately estimate significance for every single cannot fully consider nonlinear global interaction between In this paper, assuming that a complete HSI can be reconstructed...

Hyperspectral image (HSI) band selection (BS) is an important task for HSI dimensionality reduction, whose goal to select informative subset containing less redundancy. However, traditional BS methods basically work in the Euclidean domain, and thus, often neglect consider structural information of spectral bands. In this article, make full use information, a novel method termed as efficient graph convolutional self-representation (EGCSR) proposed by incorporating convolution into model....

Deep neural networks have gained increasing interest in hyperspectral image (HSI) processing. However, prior arts often neglect the high-order correlation among data points, failing to capture intraclass variations. In this letter, we present a unified network framework, termed as hypergraph-structured autoencoder (HyperAE), leverage relationship and learn robust deep representation for downstream tasks. Technically, proposed method adopts regularized by hypergraph structure backbone...

Although the extreme learning machine (ELM) has been successfully applied to hyperspectral image (HSI) classification, development of ELM is restricted by insufficient training data. In this article, we propose a novel machine-based ensemble transfer algorithm for classification named TL-ELM. TL-ELM not only retains input weights and hidden biases learned from target domain, but also utilizes instances in source domain iteratively adjust output ELM, which are used as models, then ensembles...

Recently, deep learning-based methods have made great progress in hyperspectral image (HSI) classification (HSIC). Different from ordinary images, the intrinsic complexity of HSIs data still limits performance many common convolutional neural network (CNN) models. Thus, architecture becomes more and complex to extract discriminative spectral-spatial features. For instance, 3-D CNN usually has a large number trainable parameters, thus increasing computational HSIC. In this letter, we designed...

Hyperspectral anomaly detection (HAD) aims to distinguish anomalies from background-by-background modeling. Deep learning has been applied HAD and achieves promising results. However, there exist several issues that need be addressed: 1) unrealistic Gaussian assumption on the latent representations may limit its application; 2) deep features are not well-suited due separation between feature detection; 3) lack of adequate exploitation spectral-spatial features; 4) negative effect caused by...

Hyperspectral anomaly detection (HAD) aims at distinguishing anomalies from background in an unsupervised manner. Autoencoder (AE) and its variant-based methods have achieved promising performance HAD. However, most existing neglect to exploit the local structure information of hyperspectral images (HSIs) that reflects underlying relationships between each pixel surroundings. Hence, representation capabilities networks are restricted. Moreover, reconstruction during training compels learn...