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.

MnBi₂Te₄ (MBT) is the first intrinsic magnetic topological insulator with the interaction of spin-momentum locked surface electrons and intrinsic magnetism, and it exhibits novel magnetic and topological phenomena. Recent studies suggested that the interaction of electrons and magnetism can be affected by the Mn-doped Bi₂Te₃ phase at the surface due to inevitable structural defects. Here, we report an observation of nonreciprocal transport, that is, current-direction-dependent resistance, in a bilayer composed of antiferromagnetic MBT and nonmagnetic Pt. The emergence of the nonreciprocal response below the Néel temperature confirms a correlation between nonreciprocity and intrinsic magnetism in the surface state of MBT. The angular dependence of the nonreciprocal transport indicates that nonreciprocal response originates from the asymmetry scattering of electrons at the surface of MBT mediated by magnon. Our work provides an insight into nonreciprocity arising from the correlation between magnetism and Dirac surface electrons in intrinsic magnetic topological insulators.

We propose and demonstrate a deep learning-assisted photonic approach for measuring the angle-of-arrival (AOA) with high-precision, which is suitable for long- baseline direction finding (DF). A non-uniform linear array with long- baseline is constructed to increase the precision of AOA estimation and to deal with the problem of ambiguity. The system realizes AOA-to-Voltage mapping by using dual-drive Mach Zehnder modulator (DDMZM) as phase detector and envelope detection in electrical domain. Finally, a deep neural network with long-short term memory (LSTM-DNN) is used for post-processing to establish a mapping relationship between the envelope voltage and real AOA, which not only simplifies the measurement process without phase calibration and transformation between phase difference and AOA, but also compensates the defects of the optoelectronic system and effectively improves the AOA estimation performance. Results obtained using the proposed structure demonstrate less than $0.3405^{\circ }$ errors over a - $80^{\circ }$ to $80^{\circ }$ AOA measurement range, and the mean absolute error (MAE) and root mean square errors (RMSE) are $0.1438^{\circ }$ and $0.3923^{\circ }$ respectively.

The fusion of hyperspectral and multispectral images is an important strategy for enhancing the spatial resolution of hyperspectral images. With the rapid advancement of multispectral imaging technology, the disparity in spatial resolution between multispectral and hyperspectral images is increasing. In certain scenarios, termed high-magnification, this difference can exceed 32×. Previous methods do not perform well under high-magnification fusion, and naturally, a challenge arises in achieving effective high-magnification super-resolution fusion. In light of the above analysis, this paper introduces a novel algorithm for high-magnification super-resolution fusion of hyperspectral and multispectral images based on the joint optimization of spatial and spectral information. Specifically, our algorithm consists of three stages: 1) a fast preliminary fusion stage based on the Moore-Penrose inverse and singular value correlation priors for the rapid acquisition of preliminary solutions, 2) a joint spatial-spectral optimization stage where a coupled optimization framework is constructed to achieve integrated optimization of spatial and spectral information, and 3) an error backpropagation optimization stage where an effective error optimization term is introduced to further refine the fusion performance. We conducted extensive experiments on widely employed publicly available simulated datasets and real datasets. The experimental results unequivocally indicate that our proposed methodology consistently exhibits superior fusion performance compared with state-of-the-art methods, even under the condition of ≥60× super-resolution.