Recently, deep learning has achieved breakthroughs in hyperspectral image (HSI) classification. Deep-learning-based classifiers require a large number of labeled samples for training to provide excellent performance. However, the availability of labeled data is limited due to the significant human resources and time costs of labeling hyperspectral data. Unsupervised learning for hyperspectral image classification has thus received increasing attention. In this paper, we propose a novel unsupervised framework based on a contrastive learning method and a transformer model for hyperspectral image classification. The experimental results prove that our model can efficiently extract hyperspectral image features in unsupervised situations.

Hyperspectral image (HSI) clustering is a major challenge due to the redundant spectral information in HSIs. In this paper, we propose a novel deep subspace clustering method that extracts spatial–spectral features via contrastive learning. First, we construct positive and negative sample pairs through data augmentation. Then, the data pairs are projected into feature space using a CNN model. Contrastive learning is conducted by minimizing the distances of positive pairs and maximizing those of negative pairs. Finally, based on their features, spectral clustering is employed to obtain the final result. Experimental results gained over three HSI datasets demonstrate that our proposed method is superior to other state-of-the-art methods.

Hyperspectral image (HSI) classification is the subject of intense research in remote sensing. The tremendous success of deep learning in computer vision has recently sparked the interest in applying deep learning in hyperspectral image classification. However, most deep learning methods for hyperspectral image classification are based on convolutional neural networks (CNN). Those methods require heavy GPU memory resources and run time. Recently, another deep learning model, the transformer, has been applied for image recognition, and the study result demonstrates the great potential of the transformer network for computer vision tasks. In this paper, we propose a model for hyperspectral image classification based on the transformer, which is widely used in natural language processing. Besides, we believe we are the first to combine the metric learning and the transformer model in hyperspectral image classification. Moreover, to improve the model classification performance when the available training samples are limited, we use the 1-D convolution and Mish activation function. The experimental results on three widely used hyperspectral image data sets demonstrate the proposed model’s advantages in accuracy, GPU memory cost, and running time.

Convolutional neural networks (CNNs) have been prominent in most hyperspectral image (HSI) processing applications due to their advantages in extracting local information. Despite their success, the locality of the convolutional layers within CNNs results in heavyweight models and time-consuming defects. In this study, inspired by the excellent performance of transformers that are used for long-range representation learning in computer vision tasks, we built a lightweight vision transformer for HSI classification that can extract local and global information simultaneously, thereby facilitating accurate classification. Moreover, as traditional dimensionality reduction methods are limited in their linear representation ability, a three-dimensional convolutional autoencoder was adopted to capture the nonlinear characteristics between spectral bands. Based on the aforementioned three-dimensional convolutional autoencoder and lightweight vision transformer, we designed an HSI classification network, namely the “convolutional autoencoder meets lightweight vision transformer” (CAEVT). Finally, we validated the performance of the proposed CAEVT network using four widely used hyperspectral datasets. Our approach showed superiority, especially in the absence of sufficient labeled samples, which demonstrates the effectiveness and efficiency of the CAEVT network.

Purpose: The aims of this research were to combine a-hemihydrate calcium sulfate/octacalcium phosphate (α-CSH/OCP) with sodium hyaluronate (SH) or SH sulfate (SHS) to determine whether these composites can be used as a new type of bone repair material. This study may provide a theoretical basis and new ideas for the construction of active bone repair materials and their clinical application. Methods: In this study, we combined α-CSH/OCP with SH or SHS. Scanning electron microscopy (SEM), Fourier-transform infrared (FTIR) spectroscopy, X-ray diffraction (XRD), thermogravimetric analysis (TGA), and the wettability test were performed, and porosity, setting time, in vitro degradation, and the mechanical properties of these composite materials were analyzed to evaluate the ultrastructural and physicochemical properties. We evaluated the histocompatibility of these composites by MTT assay, hemolysis, acute toxicity, and pyrogenic and intracutaneous stimulation tests. In addition, the osteogenic differentiation ability of these materials was detected in vitro using Western blot analysis and in vivo using an animal model of bone defect. Results: The α-CSH/OCP/SH composite had a compressive strength of 13.72 MPa, a porous rate of 27.45%, and the 28-day degradation rate of 64%. The MTT assay results showed that the relative proliferation rates of the α-CSH/OCP/SH group were greater than 90%. The results of the α-CSH/OCP/SH composite in the hemolysis, acute toxicity, pyrogenic, and intracutaneous stimulation tests were within the normal range. Western blot analysis indicated that the expression of bone extracellular matrix (ECM) proteins was notably upregulated and always higher in the α-CSH/OCP/SH group than in the other groups. XRD of the rabbit radius-defect model indicated that bone healing in the area implanted with α-CSH/OCP/SH was excellent approximately 9 weeks after repair. Conclusion: α-CSH/OCP/SH has very good biocompatibility and exhibits clear advantages in the induction of bone regeneration and self-repair, and this compound shows promise in the field of bone tissue engineering.

Recently, deep learning has been widely used in hyperspectral image classification. Reparameterized network as a novel deep learning method achieves competitive performance compared to other methods. Hyperspectral images have the defect of a large amount of data, and reparameterization can improve network performance without increasing network complexity because of the structure fusion. However, according to our survey there is no relevant application in hyperspectral classification. In this paper, we propose a network using reparameterized approach, which is applied in the field of hyperspectral image classification firstly. This network reparameterizes the Spectral-Spatial Residual Network (SSRN), abbreviated as RepSSRN. Experiments in three classical datasets show that RepSSRN has improved the performance of SSRN.