Cascade Superpixel Regularized Gabor Feature Fusion for Hyperspectral Image Classification

Spectral Super-Resolution via Deep Low-Rank Tensor Representation

Spectral super-resolution has attracted the attention of more researchers for obtaining hyperspectral images (HSIs) in a simpler and cheaper way. Although many convolutional neural network (CNN)-based approaches have yielded impressive results, most of them ignore the low-rank prior of HSIs resulting in huge computational and storage costs. In addition, the ability of CNN-based methods to capture the correlation of global information is limited by the receptive field. To surmount the problem, we design a novel low-rank tensor reconstruction network (LTRN) for spectral super-resolution. Specifically, we treat the features of HSIs as 3-D tensors with low-rank properties due to their spectral similarity and spatial sparsity. Then, we combine canonical-polyadic (CP) decomposition with neural networks to design an adaptive low-rank prior learning (ALPL) module that enables feature learning in a 1-D space. In this module, there are two core modules: the adaptive vector learning (AVL) module and the multidimensionwise multihead self-attention (MMSA) module. The AVL module is designed to compress an HSI into a 1-D space by using a vector to represent its information. The MMSA module is introduced to improve the ability to capture the long-range dependencies in the row, column, and spectral dimensions, respectively. Finally, our LTRN, mainly cascaded by several ALPL modules and feedforward networks (FFNs), achieves high-quality spectral super-resolution with fewer parameters. To test the effect of our method, we conduct experiments on two datasets: the CAVE dataset and the Harvard dataset. Experimental results show that our LTRN not only is as effective as state-of-the-art methods but also has fewer parameters. The code is available at https://github.com/renweidian/LTRN.

HSGAN: Hyperspectral Reconstruction From RGB Images With Generative Adversarial Network

Hyperspectral (HS) reconstruction from RGB images denotes the recovery of whole-scene HS information, which has attracted much attention recently. State-of-the-art approaches often adopt convolutional neural networks to learn the mapping for HS reconstruction from RGB images. However, they often do not achieve high HS reconstruction performance across different scenes consistently. In addition, their performance in recovering HS images from clean and real-world noisy RGB images is not consistent. To improve the HS reconstruction accuracy and robustness across different scenes and from different input images, we present an effective HSGAN framework with a two-stage adversarial training strategy. The generator is a four-level top-down architecture that extracts and combines features on multiple scales. To generalize well to real-world noisy images, we further propose a spatial-spectral attention block (SSAB) to learn both spatial-wise and channel-wise relations. We conduct the HS reconstruction experiments from both clean and real-world noisy RGB images on five well-known HS datasets. The results demonstrate that HSGAN achieves superior performance to existing methods. Please visit https://github.com/zhaoyuzhi/HSGAN to try our codes.

Fuzzy Graph Subspace Convolutional Network

Graph convolutional networks (GCNs) are a popular approach to learn the feature embedding of graph-structured data, which has shown to be highly effective as well as efficient in performing node classification in an inductive way. However, with massive nongraph-organized data existing in application scenarios nowadays, it is critical to exploit the relationships behind the given groups of data, which makes better use of GCN and broadens the application field. In this article, we propose the f uzzy g raph s ubspace c onvolutional n etwork (FGSCN) to provide a brand-new paradigm for feature embedding and node classification with graph convolution (GC) when given an arbitrary collection of data. The FGSCN performs GC on the f uzzy s ubspace ( F -space), which simultaneously learns from the underlying subspace information in the low-dimensional space as well as its neighborliness information in the high-dimensional space. In particular, we construct the fuzzy homogenous graph GF on the F -space by fusing the homogenous graph of neighborliness GN and homogenous graph of subspace GS (defined by the affinity matrix of the low-rank representation). Here, it is proven that the GC on F -space will propagate both the local and global information through fuzzy set theory. We evaluated FGSCN on 15 unique datasets with different tasks (e.g., feature embedding, visual recognition, etc.). The experimental results showed that the proposed FGSCN has significant superiority compared with current state-of-the-art methods.

Deep Network With Irregular Convolutional Kernels and Self-Expressive Property for Classification of Hyperspectral Images

This article presents a novel deep network with irregular convolutional kernels and self-expressive property (DIKS) for the classification of hyperspectral images (HSIs). Specifically, we use the principal component analysis (PCA) and superpixel segmentation to obtain a series of irregular patches, which are regarded as convolutional kernels of our network. With such kernels, the feature maps of HSIs can be adaptively computed to well describe the characteristics of each object class. After multiple convolutional layers, features exported by all convolution operations are combined into a stacked form with both shallow and deep features. These stacked features are then clustered by introducing the self-expression theory to produce final features. Unlike most traditional deep learning approaches, the DIKS method has the advantage of self-adaptability to the given HSI due to building irregular kernels. In addition, this proposed method does not require any training operations for feature extraction. Because of using both shallow and deep features, the DIKS has the advantage of being multiscale. Due to introducing self-expression, the DIKS method can export more discriminative features for HSI classification. Extensive experimental results are provided to validate that our method achieves better classification performance compared with state-of-the-art algorithms.

Hyperspectral Anomaly Detection With Tensor Average Rank and Piecewise Smoothness Constraints

Anomaly detection in hyperspectral images (HSIs) has attracted considerable interest in the remote-sensing domain, which aims to identify pixels with different spectral and spatial features from their surroundings. Most of the existing anomaly detection methods convert the 3-D data cube to a 2-D matrix composed of independent spectral vectors, which destroys the intrinsic spatial correlation between the pixels and their surrounding pixels, thus leading to considerable degradation in detection performance. In this article, we develop a tensor-based anomaly detection algorithm that can effectively preserve the spatial-spectral information of the original data. We first separate the 3-D HSI data into a background tensor and an anomaly tensor. Then the tensor nuclear norm based on the tensor singular value decomposition (SVD) is exploited to characterize the global low rank existing in both the spectral and spatial directions of the background tensor. In addition, the total variation (TV) regularization is incorporated due to the piecewise smoothness. For the anomaly component, the l2.1 norm is exploited to promote the group sparsity of anomalous pixels. In order to improve the ability of the algorithm to distinguish the anomaly from the background, we design a robust background dictionary. We first split the HSI data into local clusters by leveraging their spectral similarity and spatial distance. Then we develop a simple but effective way based on the SVD to select representative pixels as atoms. The constructed background dictionary can effectively represent the background materials and eliminate anomalies. Experimental results obtained using several real hyperspectral datasets demonstrate the superiority of the proposed method compared with some state-of-the-art anomaly detection algorithms.

Self-Paced Co-Training of Graph Neural Networks for Semi-Supervised Node Classification

Graph neural networks (GNNs) have demonstrated great success in many graph data-based applications. The impressive behavior of GNNs typically relies on the availability of a sufficient amount of labeled data for model training. However, in practice, obtaining a large number of annotations is prohibitively labor-intensive and even impossible. Co-training is a popular semi-supervised learning (SSL) paradigm, which trains multiple models based on a common training set while augmenting the limited amount of labeled data used for training each model via the pseudolabeled data generated from the prediction results of other models. Most of the existing co-training works do not control the quality of pseudolabeled data when using them. Therefore, the inaccurate pseudolabels generated by immature models in the early stage of the training process are likely to cause noticeable errors when they are used for augmenting the training data for other models. To address this issue, we propose a self-paced co-training for the GNN (SPC-GNN) framework for semi-supervised node classification. This framework trains multiple GNNs with the same or different structures on different representations of the same training data. Each GNN carries out SSL by using both the originally available labeled data and the augmented pseudolabeled data generated from other GNNs. To control the quality of pseudolabels, a self-paced label augmentation strategy is designed to make the pseudolabels generated at a higher confidence level to be utilized earlier during training such that the negative impact of inaccurate pseudolabels on training data augmentation, and accordingly, the subsequent training process can be mitigated. Finally, each of the trained GNN is evaluated on a validation set, and the best-performing one is chosen as the output. To improve the training effectiveness of the framework, we devise a pretraining followed by a two-step optimization scheme to train GNNs. Experimental results on the node classification task demonstrate that the proposed framework achieves significant improvement over the state-of-the-art SSL methods.

ZeRGAN: Zero-Reference GAN for Fusion of Multispectral and Panchromatic Images

In this article, we present a new pansharpening method, a zero-reference generative adversarial network (ZeRGAN), which fuses low spatial resolution multispectral (LR MS) and high spatial resolution panchromatic (PAN) images. In the proposed method, zero-reference indicates that it does not require paired reduced-scale images or unpaired full-scale images for training. To obtain accurate fusion results, we establish an adversarial game between a set of multiscale generators and their corresponding discriminators. Through multiscale generators, the fused high spatial resolution MS (HR MS) images are progressively produced from LR MS and PAN images, while the discriminators aim to distinguish the differences of spatial information between the HR MS images and the PAN images. In other words, the HR MS images are generated from LR MS and PAN images after the optimization of ZeRGAN. Furthermore, we construct a nonreference loss function, including an adversarial loss, spatial and spectral reconstruction losses, a spatial enhancement loss, and an average constancy loss. Through the minimization of the total loss, the spatial details in the HR MS images can be enhanced efficiently. Extensive experiments are implemented on datasets acquired by different satellites. The results demonstrate that the effectiveness of the proposed method compared with the state-of-the-art methods. The source code is publicly available at https://github.com/RSMagneto/ZeRGAN.

Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification

Hyperspectral image (HSI) classification has always been recognised as a difficult task. It is therefore a research hotspot in remote sensing image processing and analysis, and a number of studies have been conducted to better extract spectral and spatial features. This study aimed to track the variation of the spectrum in hyperspectral images from a sequential data perspective to obtain more distinguishable features. Based on the characteristics of optical flow, this study introduces an optical flow technique for the extraction of spectral flow that denotes the spectral variation and implements a dense optical flow extraction method based on deep matching. Lastly, the extracted spectral flow are combined with the original spectral features and input into a commonly used support vector machine (SVM) classifier to complete the classification. Extensive classification experiments on three benchmark HSI test sets show that the classification accuracy obtained by the spectral flow extracted in this study (SpectralFlow) is higher than traditional spatial feature extraction methods, texture feature extraction methods, and the latest deep-learning-based methods. Furthermore, the proposed method can produce finer classification thematic maps, thereby demonstrating strong practical application potential.

Non-Contrasted CT Radiomics for SAH Prognosis Prediction

Subarachnoid hemorrhage (SAH) denotes a serious type of hemorrhagic stroke that often leads to a poor prognosis and poses a significant socioeconomic burden. Timely assessment of the prognosis of SAH patients is of paramount clinical importance for medical decision making. Currently, clinical prognosis evaluation heavily relies on patients' clinical information, which suffers from limited accuracy. Non-contrast computed tomography (NCCT) is the primary diagnostic tool for SAH. Radiomics, an emerging technology, involves extracting quantitative radiomics features from medical images to serve as diagnostic markers. However, there is a scarcity of studies exploring the prognostic prediction of SAH using NCCT radiomics features. The objective of this study is to utilize machine learning (ML) algorithms that leverage NCCT radiomics features for the prognostic prediction of SAH. Retrospectively, we collected NCCT and clinical data of SAH patients treated at Beijing Hospital between May 2012 and November 2022. The modified Rankin Scale (mRS) was utilized to assess the prognosis of patients with SAH at the 3-month mark after the SAH event. Based on follow-up data, patients were classified into two groups: good outcome (mRS ≤ 2) and poor outcome (mRS > 2) groups. The region of interest in NCCT images was delineated using 3D Slicer software, and radiomic features were extracted. The most stable and significant radiomic features were identified using the intraclass correlation coefficient, t-test, and least absolute shrinkage and selection operator (LASSO) regression. The data were randomly divided into training and testing cohorts in a 7:3 ratio. Various ML algorithms were utilized to construct predictive models, encompassing logistic regression (LR), support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and multi-layer perceptron (MLP). Seven prediction models based on radiomic features related to the outcome of SAH patients were constructed using the training cohort. Internal validation was performed using five-fold cross-validation in the entire training cohort. The receiver operating characteristic curve, accuracy, precision, recall, and f-1 score evaluation metrics were employed to assess the performance of the classifier in the overall dataset. Furthermore, decision curve analysis was conducted to evaluate model effectiveness. The study included 105 SAH patients. A comprehensive set of 1316 radiomics characteristics were initially derived, from which 13 distinct features were chosen for the construction of the ML model. Significant differences in age were observed between patients with good and poor outcomes. Among the seven constructed models, model_SVM exhibited optimal outcomes during a five-fold cross-validation assessment, with an average area under the curve (AUC) of 0.98 (standard deviation: 0.01) and 0.88 (standard deviation: 0.08) on the training and testing cohorts, respectively. In the overall dataset, model_SVM achieved an accuracy, precision, recall, f-1 score, and AUC of 0.88, 0.84, 0.87, 0.84, and 0.82, respectively, in the testing cohort. Radiomics features associated with the outcome of SAH patients were successfully obtained, and seven ML models were constructed. Model_SVM exhibited the best predictive performance. The radiomics model has the potential to provide guidance for SAH prognosis prediction and treatment guidance.

Deep Feature Aggregation Framework Driven by Graph Convolutional Network for Scene Classification in Remote Sensing

Scene classification of high spatial resolution (HSR) images can provide data support for many practical applications, such as land planning and utilization, and it has been a crucial research topic in the remote sensing (RS) community. Recently, deep learning methods driven by massive data show the impressive ability of feature learning in the field of HSR scene classification, especially convolutional neural networks (CNNs). Although traditional CNNs achieve good classification results, it is difficult for them to effectively capture potential context relationships. The graphs have powerful capacity to represent the relevance of data, and graph-based deep learning methods can spontaneously learn intrinsic attributes contained in RS images. Inspired by the abovementioned facts, we develop a deep feature aggregation framework driven by graph convolutional network (DFAGCN) for the HSR scene classification. First, the off-the-shelf CNN pretrained on ImageNet is employed to obtain multilayer features. Second, a graph convolutional network-based model is introduced to effectively reveal patch-to-patch correlations of convolutional feature maps, and more refined features can be harvested. Finally, a weighted concatenation method is adopted to integrate multiple features (i.e., multilayer convolutional features and fully connected features) by introducing three weighting coefficients, and then a linear classifier is employed to predict semantic classes of query images. Experimental results performed on the UCM, AID, RSSCN7, and NWPU-RESISC45 data sets demonstrate that the proposed DFAGCN framework obtains more competitive performance than some state-of-the-art methods of scene classification in terms of OAs.

Graph-in-Graph Convolutional Network for Hyperspectral Image Classification

With the development of hyperspectral sensors, accessible hyperspectral images (HSIs) are increasing, and pixel-oriented classification has attracted much attention. Recently, graph convolutional networks (GCNs) have been proposed to process graph-structured data in non-Euclidean domains and have been employed in HSI classification. But most methods based on GCN are hard to sufficiently exploit information of ground objects due to feature aggregation. To solve this issue, in this article, we proposed a graph-in-graph (GiG) model and a related GiG convolutional network (GiGCN) for HSI classification from a superpixel viewpoint. The GiG representation covers information inside and outside superpixels, respectively, corresponding to the local and global characteristics of ground objects. Concretely, after segmenting HSI into disjoint superpixels, each one is converted to an internal graph. Meanwhile, an external graph is constructed according to the spatial adjacent relationships among superpixels. Significantly, each node in the external graph embeds a corresponding internal graph, forming the so-called GiG structure. Then, GiGCN composed of internal and External graph convolution (EGC) is designed to extract hierarchical features and integrate them into multiple scales, improving the discriminability of GiGCN. Ensemble learning is incorporated to further boost the robustness of GiGCN. It is worth noting that we are the first to propose the GiG framework from the superpixel point and the GiGCN scheme for HSI classification. Experiment results on four benchmark datasets demonstrate that our proposed method is effective and feasible for HSI classification with limited labeled samples. For study replication, the code developed for this study is available at https://github.com/ShuGuoJ/GiGCN.git.