Deep neural networks have demonstrated remarkable reconstruction for single-image super-resolution (SISR). However, most existing CNN-based SISR methods directly learn the relation between low-resolution (LR) and high-resolution (HR) images, neglecting to explore the recurrence of internal patches, hence hindering the representational power of CNNs. In this paper, we propose a novel single image Super-Resolution network based on Graph ATtention network (SRGAT) to make full use of the internal patch-recurrence in a natural image. The proposed model employs a feature mapping block with a recurrent structure to refine low-level representations with high-level information. Especifically, the feature mapping block contains a parallel graph similarity branch and a content branch, where the graph similarity branch aims at exploiting the similarity and symmetry across different image patches in low-resolution feature space and provides additional priors for the content branch to enhance texture details. Specifically, we consider the internal patch-recurrence of an image by constructing a graph network on image feature patches. In this way, the information from neighboring patches can be interacted using graph attention network (GAT) to help it recover additional textures, which complements the textures learned from the content branch. Extensive quantitative and qualitative evaluations on five benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art super-resolution methods.

Deep subspace clustering network has shown its effectiveness in hyperspectral image (HSI) clustering. However, there are two major challenges that need to be addressed: 1) lack of effective supervision for feature learning; and 2) negative effect caused by the high redundancy of the global dictionary atoms. In this article, we propose an end-to-end trainable network for HSI clustering. Specifically, to ensure the extracted features are well-suited to subsequent subspace clustering, the cluster assignments with high confidence are employed as pseudo-labels to supervise the feature learning process. Then, an adaptive self-expressive coefficient matrix initialization strategy is designed to reduce the dictionary redundancy, where the spectral similarity between each target sample and its neighbors is modeled via the k-nearest neighbor graph to guide the initialization. Experimental results on three public HSI datasets demonstrate the effectiveness of the proposed method. In particular, our method outperforms several state-of-the-art HSI clustering methods, and achieves overall accuracy of 100% on both SalinasA and Pavia University datasets.

Hyperspectral anomaly detection (HAD) aims to distinguish anomalies from background-by-background modeling. Deep learning has been applied to HAD and achieves promising detection results. However, there exist several issues that need to be addressed: 1) unrealistic Gaussian assumption on the latent representations may limit its application; 2) deep features are not well-suited to anomaly detection due to the separation between feature learning and anomaly detection; 3) lack of adequate exploitation of spectral-spatial features; 4) negative effect caused by spectral band redundancy. In this article, we propose an end-to-end trainable deep one-class classification network for HAD. Specifically, a minimal enclosing hypersphere is trained to involve the deep features of background samples. These background samples are selected by a density clustering-based method. In this way, feature learning and anomaly detection are incorporated into a unified framework. Meanwhile, there is no explicit Gaussian assumption on the background features. Moreover, due to the complementarity of spectral and spatial features, a novel feature fusion strategy is proposed to fuse spectral and spatial features extracted by a two-stream deep convolutional autoencoder network. Finally, a band attention module is used to automatically learn small weights for redundant bands and thus reduce the negative effect caused by redundant bands. Experimental results on five public datasets demonstrate the superiority of the proposed method compared to several state-of-the-art HAD methods in the detection performance.

Hyperspectral anomaly detection (HAD) aims at distinguishing anomalies from background in an unsupervised manner. Auto-encoder and its variant-based methods have achieved promising detection performance in HAD. However, most existing methods neglect to exploit the local structure information of hyperspectral images that reflects the underlying relationships between each pixel and its surroundings. Hence, the representation capabilities of the networks are restricted. Moreover, reconstruction of anomalies during training compels the networks to learn abnormal patterns, and thus reduces the spectral differences between background and anomalies. To address these problems, a spectral difference guided graph attention auto-encoder network is proposed for HAD. Specifically, the relationships among samples are modeled by a graph attention encoder, where a spectral sharpening constraint is introduced to guide the attention coefficient learning. In this way, the encoder can also represent the spectral differences between central nodes and their neighbors. Then, a learnable graph attention decoder is constructed to reconstruct node attributes and obtain the node reconstruction errors for HAD. Besides, a background purification method is proposed to generate superpixel-level samples to suppress anomaly reconstruction during training. Extensive quantitative and qualitative evaluations on six real datasets and one synthetic dataset show that the proposed method achieves competitive detection performance as compared to the state-of-the-art HAD methods.

Recently, state-of-the-art classification performance of natural images has been obtained by self-supervised learning (S2L) as it can generate latent features through learning between different views of the same images. However, the latent semantic information of similar images has hardly been exploited by these S2L-based methods. Consequently, to explore the potential of S2L between similar samples in hyperspectral image classification (HSIC), we propose the nearest neighboring self-supervised learning (N2SSL) method, by interacting between different augmentations of reliable nearest neighboring pairs (RN2Ps) of HSI samples in the framework of bootstrap your own latent (BYOL). Specifically, there are four main steps: pretraining of spectral spatial residual network (SSRN)-based BYOL, generation of nearest neighboring pairs (N2Ps), training of BYOL based on RN2P, final classification. Experimental results of three benchmark HSIs validated that S2L on similar samples can facilitate subsequent classification. Moreover, we found that BYOL trained on an un-related HSI can be fine-tuned for classification of other HSIs with less computational cost and higher accuracy than training from scratch. Beyond the methodology, we present a comprehensive review of HSI-related data augmentation (DA), which is meaningful to future research of S2L on HSIs.

With great significance in military and civilian applications, subpixel target detection is of great interest in hyperspectral remote sensing. The subpixel targets usually also need to be unmixed to identify their components. Traditionally, these subpixel targets are first detected and then unmixed to obtain their corresponding abundances. Therefore, target detection and target unmixing are independently performed. However, there are potential relations between these two processes that need to be investigated. In this article, we integrate these two processes using iterative constrained sparse representation. The main idea of this algorithm is that each pixel can be linearly and sparsely represented by the prior target spectra and several background endmembers extracted from its neighborhood. Moreover, the sum-to-one and nonnegativity constraints are introduced to ensure the sparse representation coefficients to have physical meaning. Specifically, the background endmembers are automatically extracted from the local background based on an iterative process. Then, the test pixel is represented by these extracted endmembers. Finally, the detection output is determined by the total target abundance and the residuals. The main innovation of this method is that it implements detection and unmixing of subpixel target simultaneously, even if the local background is contaminated by target signals. Experiments conducted on both synthetic and real hyperspectral datasets demonstrate that the proposed detector achieves an outstanding performance on detection and unmixing.