Few-shot learning (FSL) through the training of few labeled samples in the source domain and fine-tuning in target domain has gotten increasing attention in hyperspectral images (HSI) classification. However, in current FSL for HSI classification (HSIC), the number of classes trained in the source domain feature extractor is contingent upon the aligned class number with task classes, which restricts the availability and generalization of the transferable knowledge learned in the source domain. In this article, we propose a few-shot learning with class-number non-aligned training and feature differential network for hyperspectral image classification. Firstly, a class-number non-aligned FSL training framework on multiple independent sources is established, where each source trains respective classes, eliminating the need for aligning the number of classes with the target's. Secondly, in order to learn the feature brought by different domains at different scales, an attention-guided cross-scale feature differential network is constructed to obtain feature differentials between neighboring layers through a feature differential unit (FDU), which extracts detailed pixel's differential information and facilitates to exploit feature variations at different scales. Furthermore, to alleviate the training burden generated by multiple source domains from the non-aligned training strategy, a hybrid loss function is devised to augment the inter-class distance while reducing the intra-class distance. Experiments conducted on three public hyperspectral datasets demonstrate that the proposed model outperforms existing FSL methods for Hyperspectral image classification.

Hyperspectral images (HSI) have spectral variability, which leads to spectral dependence in adjacent and non-adjacent regions, and this dependence is essential for the classification of regions with mixed pixels. Current neural architecture search (NAS) methods have achieved significant advantages in HSI classification, but these methods cannot capture spectral dependence in non-adjacent regions because only use feedforward connections. Meanwhile, the cost of the search process in NAS is proportional to the scale of the search space, which limits the expansion of the search space. To address these issues, we propose a sparse-coding-inspired feedback neural architecture search (SCIF-NAS) method for HSI classification. Firstly, we view HSI samples as sequences and introduce a feedback mechanism in NAS to model the spectral dependence of non-adjacent regions to mitigate the effects of spectral variation. Secondly, we design several feedforward operations according to the characteristics of HSI, to form the search space together with feedback operations. Meanwhile, a sparse-coding-inspired NAS accelerated strategy is introduced to alleviate the search time burden caused by the expansion of search space. Thirdly, we integrate center loss with cross-entropy loss to construct a hybrid loss function that helps to obtain a better classification boundary. Finally, we conduct experiments on three popular HSI benchmarks, which show that SCIF-NAS outperforms the state-of-the-art methods in HSI classification.

Few-shot learning (FSL) has achieved promising performance in hyperspectral image classification (HSIC) with few labeled samples by designing a proper embedding feature extractor. However, the performance of embedding feature extractors relies on the design of efficient deep convolutional neural network architectures, which heavily depends on the expertise knowledge. Particularly, FSL requires extracting discriminative features effectively across different domains, which makes the construction even more challenging. In this paper, we propose a novel neural architecture search-based FSL model for HSI classification, called HCFSL-NAS. Three novel strategies are proposed in this work. First, a neural architecture search-based embedding feature extractor is developed to the FSL in HSIC, whose search space includes a group of proposed multi-scale convolutions with channel attention. Second, a multi-source learning framework is employed to aggregate abundant heterogeneous and homogeneous source data, which enables the powerful generalization of network to the HSIC with only few labeled samples. Finally, the pointwise-based cross-entropy loss and the pairwise-based adaptive sparse loss are jointly optimized to maximize inter-class distance and minimize the distance within a class simultaneously. Experimental results on four publicly hyperspectral data sets demonstrate that HCFSL-NAS outperforms both the exiting FSL methods and supervised learning methods for HSI classification with only few labeled samples. Code is available at: https://github.com/xh-captain/HCFSL-NAS.

Hyperspectral image (HSI) classification based on neural architecture search (NAS) is a currently attractive frontier as it not only automatically searches complex neural network architecture, but also avoids professional knowledge and experience design, and alleviates the lacking of generalization ability as well when dealing with a new classification task. However, the existing HSI classification based on NAS has some drawbacks: 1) A huge number of training parameters and high calculations are inductive to over-fitting and high complexity. 2) Efficient operators are lacking in the search space which can distinguish spatial locations and spectral features in different bands. Furthermore, as the category samples in HSI data show a serious long-tail distribution phenomenon, HSI classification remains challenging. To address these issues, we propose a lightweight HSI classification model LMSS-NAS integrating multi-scale spectral-spatial attention. The main work includes three-fold: 1) In order to reduce the number of model parameters and promote spectral-spatial feature fusion, a new lightweight efficient search space is designed, which consists of three equivalent lightweight convolution operators with multiple receptive fields. 2) To fully use the spectral-spatial correlation of HSI, a cube-to-pixel classification framework is designed to mine the local spatial and spectral context. 3) Focal loss and label smoothing loss in computer vision tasks are jointly migrated to LMSS-NAS to improve the unbalanced samples’ classification and model robustness. Experimental results on four public hyperspectral data sets show that the proposed method can achieve competitive classification performance as well as low computational cost. Code is available at: https://github.com/xh-captain/LMSS-NAS.

Poleward moving auroral forms (PMAFs) are one of the most common dayside auroral phenomena, which are important to study the dynamics of the polar cusp. In this article, we propose an unsupervised auroral optical flow (UnAurFlow) model for recognizing the PMAFs from auroral image sequences captured by all-sky imagers. Since auroral shape and illumination change continuously and randomly during the evolution, and auroral motion violates the brightness constancy assumption, UnAurFlow designs an auroral deformation detection module based on bidirectional optical flow and exploits the census transform to compensate for the auroral luminosity changes. UnAurFlow is trained in an unsupervised manner, which circumvents the difficulty of manually labeling auroral optical flow. The validity of UnAurFlow is qualitatively and quantitatively evaluated using auroral observations in 2003–2005 at the Arctic Yellow River Station. Based on the auroral optical flow computed by UnAurFlow, and combining with ResNet and the attention mechanism, PMAFs are automatically recognized with a precision of 84.77% from continuous auroral observations, which outperform the state-of-the-art unsupervised optical flow algorithms. The temporal occurrence distribution of PMAFs is prenoon–postnoon asymmetric under negative interplanetary magnetic field (IMF) By conditions, which is in good agreement with the previous statistical study.