The very high spectral resolution in hyperspectral images (HSIs) offers an opportunity to detect subtle land-cover changes. However, the availability of HSIs acquired from different platforms requires the development of change detection (CD) methods capable of processing HSIs with different spatial resolutions. In this article, we propose a general end-to-end subpixel convolution-based residual network (SPCNet) to accomplish the CD task between high spatial resolution (HR) and low spatial resolution (LR) HSIs. To effectively tackle the resolution matching issue, a super-resolution (SR) block with an efficient subpixel convolution layer is introduced to upscale the LR feature maps into HR maps. The subpixel convolution layer can fully explore the subpixel context information by learning an array of upscaling filters. Moreover, the designed SPC module is embedded into the LR branch to generate more discriminative representations. More importantly, the SPC module as a plug-and-play unit has the potential to be embedded into other baseline networks to enhance the feature learning capability. Experimental results on four HSI datasets demonstrate the effectiveness of the proposed SPCNet.

For hyperspectral image classification (HIC) tasks, most uncertainty-based active learning (AL) methods only consider the uncertainty, without considering the diversity of actively selected samples and the budget of expert labeling. In this paper, we propose a collaborative active learning (CAL) framework to address this problem. The proposed framework consists of two well-designed base classifiers and an ingenious CAL scheme that takes into account both the uncertainty and diversity of actively selected samples and the cost of expert annotation. Specifically, get benefit from the capsule networks’ ability to accurately identify and locate features, we design two improved capsule networks. For these two networks, we call the first CapsViT (Capsule Vision Transformer), which introduces Vision Transformer (ViT) into the capsule network (CapsNet) to learn the global relationship between the capsule features. We call the second CapsGLOM (Capsule GLOM), the basic structure of this network is derived from the GLOM system proposed by Geoffrey Hinton, we learn from the way CapsNet constructs the primary capsules to improve its implementation details. CapsViT and CapsGLOM are used as the two base classifiers in the proposed CAL framework to select the most informative samples according to the CAL scheme under the premise of fully considering the cost of expert annotation. Experimental results on four benchmark hyperspectral image data sets show that our proposed CAL framework can achieve satisfactory classification results. At the same time, compared with other advanced deep models, our proposed CapsViT and CapsGLOM are also competitive in the supervised HIC tasks. The source code can be available online (https://github.com/swiftest/CAL).

Studies on the classification of hyperspectral images (HSIs) based on deep learning are in full swing, especially the spectral–spatial dependent global learning (SSDGL) framework, which is both efficient and robust. However, the global convolutional long short-term memory (GCL) module under this framework fails to take full consideration of the spectral characteristics contained in HSIs, and the hierarchically balanced (H-B) sampling strategy introduced in this framework prevents the training process from converging smoothly. In this article, we develop a novel regularized spectral–spatial global learning (RSSGL) framework. Compared with SSDGL, the proposed framework mainly makes three improvements. Above all, aiming at the problem that the GCL module used in SSDGL cannot fully tap the local spectral dependence, we apply 3-D convolution to the gated units of long short-term memory (LSTM) as an alternative to the GCL module for adjacent and nonadjacent spectral dependencies learning. Furthermore, to extract the most discriminative features, an improved statistical loss regularization term is developed, in which we introduce a simple but effective diversity-promoting condition to make it more reasonable and suitable for deep metric learning in HSI classification. Finally, to effectively address the performance oscillation caused by the H-B sampling strategy, the proposed framework adopts an early stopping strategy to save and restore the optimal model parameters, making it more flexible and stable. Experiments conducted on three representative datasets show that the proposed RSSGL has superior classification performance compared with the existing relatively excellent research methods. The source code is released at https://github.com/swiftest/RSSGL .

Vision Transformer (ViT) has been thoroughly explored in hyperspectral image (HSI) classification (HIC). Nevertheless, current ViT-based approaches still acquire discriminative features, resulting in relatively limited generalization capabilities when confronted with the challenges posed by high intraclass variances and interclass similarities commonly observed in HSI data. Moreover, most of these methods fail to adequately emphasize the significance of the central pixel in HIC. To address the aforementioned challenges, we introduce a masked ViT (MViT) for HIC. First and foremost, MViT endeavors for the first time to introduce the masking operations in supervised models to learn more robust patterned features instead of distinguishable features, thereby bestowing it with outstanding generalization performance. Secondly, during the training phase of MViT, when conducting the random masking operations on the embedded features, we deliberately retain the embedding corresponding to the central pixel to guarantee the effectiveness of the model and emphasize the importance of the central pixel in HIC. Finally, MViT will deactivate the masking operations during the testing phase and utilize all the embedded features to accomplish the classification task, thereby enabling the model to fully exploit its recognition capabilities. On top of that, MViT is an extremely lightweight model, and by introducing the masking operations during the training phase, its training speed becomes unprecedentedly rapid. Experiments conducted on four publicly accessible datasets demonstrate that MViT can consistently achieve excellent or even the optimal classification results in comparison with the most advanced methods. The source code was powered by Jupyter and released at https://github.com/swiftest/MViT.

As the most prevalent self-supervised representation learning (SSRL) model, the masked auto-encoder (MAE) has been gradually investigated in semi-supervised hyperspectral image (HSI) classification (SHIC). However, the majority of the current approaches augment MAE merely from the application perspective or by introducing a weak regularization term, and do not comprehensively consider the challenges posed by the high intra-class variances and inter-class similarities that often appear in HSI data. In this article, we present a regularized MAE (RMAE) to address the aforementioned problems. Specifically, within the framework of MAE, we introduce a self-designed induced Transformer block, using a small number of visible patches to learn the embeddings of patches with larger receptive fields. The learned embeddings are used to reconstruct the corresponding patches and an induced reconstruction loss is calculated. This strategy creates a much harder task for masked image modeling (MIM), and the induced Transformer block is lightweight and imposes negligible computational burden overhead the underlying MAE framework. Additionally, by rethinking the masking operations, we develop a masked convolutional neural network (MCNN), uncovering the principle of MAE and affirming the efficacy of RMAE. Finally, we present two metrics: the mean intra-class distance, and the mean inter-class distance. Based on the metrics we give two criteria to evaluate the performance of an SSRL model, providing new coordinate for the research in SSRL-based SHIC. Experiments conducted on four publicly accessible data sets show that RMAE outperforms state-of-the-art methods. The source code was powered by Jupyter and released at https://github.com/swiftest/RMAE.

In recent years, Vision Transformers (ViTs) have gained significant traction in the field of hyperspectral image classification due to their advantages in modeling long-range dependency relationships between spectral bands and spatial pixels. However, after stacking multiple Transformer encoders, challenges pertaining to information degradation may emerge during the forward propagation. That is to say, existing Transformer-based methods exhibit certain limitations in retaining and effectively utilizing information throughout their forward transmission. To tackle these challenges, this paper proposes a novel dual-branch spatial–spectral Transformer model that incorporates similarity propagation (DBSSFormer-SP). Specifically, this model first employs a Hybrid Pooling Spatial Channel Attention (HPSCA) module to integrate global information by pooling across different dimensional directions, thereby enhancing its ability to extract salient features. Secondly, we introduce a mechanism for transferring similarity attention that aims to retain and strengthen key semantic features, thus mitigating issues associated with information degradation. Additionally, the Spectral Transformer (SpecFormer) module is employed to capture long-range dependencies among spectral bands. Finally, the extracted spatial and spectral features are fed into a multilayer perceptron (MLP) module for classification. The proposed method is evaluated against several mainstream approaches on four public datasets. Experimental results demonstrate that DBSSFormer-SP exhibits excellent classification performance.