The problem of insufficient labeled samples has restricted the application of deep learning method in hyperspectral image classification tasks. Fusion of remote sensing images from different sources such as hyperspectral image, Lidar is a common strategy to improve the classification accuracy. However, obtaining multi-source registered remote sensing images of the same area is time-consuming, which limits the application of multi-source strategy in practice. Motivated by the recent success of large models in different fields, we propose to extract depth information from large models and fuse it with hyperspectral images to improve the small sample classification accuracy. Specifically, we use the pre-trained foundation large model to estimate the depth information of hyperspectral images as the depth features, and then input the original spectral features and depth features into the support vector machine to complete the classification. In order to further improve the classification accuracy, we propose to use the sliding window method to extract the depth features of different bands, so as to obtain more rich depth features. A large number of classification experiments on six benchmark datasets verify the effectiveness of the proposed method.

As for hyperspectral images (HSIs), the discrepancy of contiguous spectral information should be the main basis for the identification of ground objects. Due to the difficulty of spectral sequence coding and the spectrum similarity between categories, successful deep-learning-based classification methods always attempt to capture the spatial information to improve the accuracy by convolutional neural networks (CNNs) or other excellent spatial feature extractors. However, extracting spatial features is generally accompanied by the distortion of ground objects distribution and categories boundary. To effectively represent spectral features, the SpectralFormer based on transformer backbone can better capture the long-term dependence of the spectrum, which improves the performance of spectral feature methods significantly. However, it is still unable to compete with advanced spectral–spatial feature methods. To exploit the discriminative advantage of the spectrum fully, this letter introduces an efficient sparse-to-dense optical flow estimation method to track the spectrum variation in the HSI. Then, we take such a variation as a spectrum motion feature to enhance the original spectrum. At last, we continue to use the SpectralFormer to encode the concatenated spectrum sequence for classification. Extensive experiments show that the SpectralFormer enhanced by the spectrum motion feature (SF-SMF) significantly improves the performance of spectral feature methods, even surpassing advanced spectral–spatial feature methods. SF-SMF can avoid interference with additional spatial information to obtain exquisite whole-domain classification maps, showing its practical value. The codes will be public athttps://github.com/sssssyf/SF-SMF.

In recent years, deep-learning-based hyperspectral image (HSI) classification methods have achieved significant development and gradually become widely applied. The existing advanced methods can achieve near-saturation performance with sufficient labels in a closed-set environment (CSE), i.e., training set and test set are all known categories of ground objects. However, the real world is usually open because of the diversity of land covers, i.e., test-set exists unknown categories that are not labeled in the training set. Therefore, the prevalent advanced CSE methods still cannot effectively and robustly handle unknown categories of ground objects in an open-set environment (OSE). Therefore, we propose a spectral-spatial MLP-like network with reciprocal points learning (SSMLP-RPL) to improve the performance of open-set HSI classification. First, a feature learning framework based on reciprocal points learning (RPL) is constructed to model the extra-category space and reduce the risk of open space. The learned feature space enables to enlarge the distance between the known and unknown categories. Besides, we further propose to utilize a learnable dynamic threshold of each known category to effectively distinguish the unknown categories and improve open performance of the model. Second, to enhance the capacity of feature learning, a spectral-spatial MLP-like network (SSMLP) is designed to capture the spectral-spatial feature merely with a series of fully-connected (FC) layers, which mainly involve SpeFC and SpaFC two modules. Among them, the SpaFC module enables to model spacial semantics, and the SpeFC module enables to model long-distance spectral dependence. Extensive experiments on three benchmark HSIs show that SSMLP-RPL has a competitive performance both in CSE and OSE and even surpasses currently advanced closed-set and open-set HSI classification methods. As an end-to-end HSI classification framework of MLP-backbone, SSMLP network can compete with the advanced works based on CNN and transformer. The code will be open at: https://github.com/sssssyf/SSMLP-RPL.

With the rapid development of remote sensing data acquisition technology, there are multimodal images over the same observed scenes. These multimodal remote sensing images could provide complementary valuable information for land cover classification. In this article, we propose a novel self-supervised feature learning and few-shot classification model for multimodal remote sensing images, called S2FL. Specifically, a contrastive learning architecture is investigated to learn spatial feature representations from very high resolution (VHR) image. And the spectral features from hyperspectral data are integrated with learned spatial features for few-shot land cover classification. Classification experiments are conducted on a widely-used dataset, i.e., Houston 2018, to verify the effectiveness and superiority of the proposed S2FL model compared with several state-of-the-art baseline approaches.

Although deep learning-based approaches have made significant progress in remote sensing image classification, the supervised learning paradigm has shortcomings under a limited number of labeled samples, which restricts the classification performance to a great extent. In this article, we investigate an effective self-supervised feature representation architecture (SSFR) for multimodal remote sensing images few-shot land cover classification. Specifically, we exploit multiview learning strategy to construct multiple views from multimodal remote sensing images. This method builds several complementary views of the same observed scenes from hyperspectral images or different modalities of remote sensing data. Then we build the deep feature extractor to learn high-level feature representations from each view via contrastive learning. The contrastive learning aggregates the samples of the same scene while separating samples of different scenes in the latent space, and this process does not require any labeled information. What’s more, to learn more robust features from different views, we utilize multitask learning strategy to train the feature extraction network. Finally, a lightweight machine learning method is employed to classify the learned features using a few annotated samples. To further demonstrate the self-supervised feature learning capability of the proposed model, we train the feature representation network in multiple source datasets. Comprehensive feature learning and classification experiments have certified the effectiveness and superiority of the proposed method.

Deep learning models have shown great potential in remote sensing image processing and analysis. Nevertheless, there are insufficient labeled samples to train deep networks, which seriously affects the performance of these models. To resolve this contradiction, we propose a generative self-supervised feature learning (S2FL) architecture for multimodal remote sensing image land cover classification. Specifically, multiple complementary observed views are constructed from multimodal remote sensing images, which are employed for following generative self-supervised learning. The proposed S2FL architecture is capable of extracting high-level meaningful feature representations from multiview data, and this process does not require any labeled information, providing a feasible solution to relieve the urgent need for annotated samples. The learned features are normalized and merged with corresponding spectral information to further improve the discriminative capability of feature representations, and we utilize these fused features for land cover classification. Compared with existing supervised, semi-supervised, and self-supervised approaches, the proposed generative self-supervised model achieves superior performance in terms of feature learning and land cover classification, especially in the small sample classification case.

The existing hyperspectral image (HSI) classification encounters the obstacle of improving the classification accuracy with limited labeled samples. In this context, as a typical implementation of meta-learning, few-shot learning (FSL) makes the model learn by episodic training on source HSI, which has achieved significant improvements in small sample classification of target HSI. However, the existing FSL methods lack explicit consideration and exploration of the association between pixels, especially the intraclass association and interclass association between pixels in the support set and query set. To mitigate these issues, an FSL method based on edge-labeling graph neural network (FSL-EGNN) is proposed for small sample classification of HSI, which is the first attempt to explicitly quantify the associations between pixels by exploiting EGNN in HSI few-shot classification (FSC). Specifically, based on graph construction of HSI, episodic training is performed on the existing source HSI. During training, EGNN is used to predict the edge labels on the graph, thereby explicitly modeling the intraclass similarity and interclass dissimilarity between pixels of HSI. After the trained model is fine-tuned, it can realize FSC on the unseen target HSI. Experiments conducted on three benchmark HSI datasets demonstrate that the proposed FSL-EGNN outperforms the existing state-of-the-art methods with limited labeled samples.

In this study, we develop a novel deep hierarchical vision transformer (DHViT) architecture for hyperspectral and light detection and ranging (LiDAR) data joint classification. Current classification methods have limitations in heterogeneous feature representation and information fusion of multi-modality remote sensing data (e.g., hyperspectral and LiDAR data), these shortcomings restrict the collaborative classification accuracy of remote sensing data. The proposed deep hierarchical vision transformer architecture utilizes both the powerful modeling capability of long-range dependencies and strong generalization ability across different domains of the transformer network, which is based exclusively on the self-attention mechanism. Specifically, the spectral sequence transformer is exploited to handle the long-range dependencies along the spectral dimension from hyperspectral images, because all diagnostic spectral bands contribute to the land cover classification. Thereafter, we utilize the spatial hierarchical transformer structure to extract hierarchical spatial features from hyperspectral and LiDAR data, which are also crucial for classification. Furthermore, the cross attention (CA) feature fusion pattern could adaptively and dynamically fuse heterogeneous features from multi-modality data, and this contextual aware fusion mode further improves the collaborative classification performance. Comparative experiments and ablation studies are conducted on three benchmark hyperspectral and LiDAR datasets, and the DHViT model could yield an average overall classification accuracy of 99.58%, 99.55%, and 96.40% on three datasets, respectively, which sufficiently certify the effectiveness and superior performance of the proposed method.

Deep learning methods have recently been successfully explored for hyperspectral image (HSI) classification. However, training a deep-learning classifier notoriously requires hundreds or thousands of labeled samples. In this paper, a deep few-shot learning method is proposed to address the small sample size problem of HSI classification. There are three novel strategies in the proposed algorithm. First, spectral–spatial features are extracted to reduce the labeling uncertainty via a deep residual 3-D convolutional neural network. Second, the network is trained by episodes to learn a metric space where samples from the same class are close and those from different classes are far. Finally, the testing samples are classified by a nearest neighbor classifier in the learned metric space. The key idea is that the designed network learns a metric space from the training data set. Furthermore, such metric space could generalize to the classes of the testing data set. Note that the classes of the testing data set are not seen in the training data set. Four widely used HSI data sets were used to assess the performance of the proposed algorithm. The experimental results indicate that the proposed method can achieve better classification accuracy than the conventional semisupervised methods with only a few labeled samples.

Hyperspectral image classification has become a research focus in recent literature. However, well-designed features are still open issues that impact on the performance of classifiers. In this paper, a novel supervised deep feature extraction method based on siamese convolutional neural network (S-CNN) is proposed to improve the performance of hyperspectral image classification. First, a CNN with five layers is designed to directly extract deep features from hyperspectral cube, where the CNN can be intended as a nonlinear transformation function. Then, the siamese network composed by two CNNs is trained to learn features that show a low intraclass and high interclass variability. The important characteristic of the presented approach is that the S-CNN is supervised with a margin ranking loss function, which can extract more discriminative features for classification tasks. To demonstrate the effectiveness of the proposed feature extraction method, the features extracted from three widely used hyperspectral data sets are fed into a linear support vector machine (SVM) classifier. The experimental results demonstrate that the proposed feature extraction method in conjunction with a linear SVM classifier can obtain better classification performance than that of the conventional methods.