In recent years, pixel-wise hyperspectral image (HSI) classification has received growing attention in the field of remote sensing. Plenty of spectral-spatial convolutional neural network (CNN) methods with diverse attention mechanisms have been proposed for HSI classification due to the attention mechanisms being able to provide more flexibility over standard convolutional blocks. However, it remains a challenge to effectively extract multi-scale features of high-resolution HSI in a real-world complex environment. In this paper, we propose a pyramidal multi-scale spectral-spatial convolutional network with polarized self-attention for pixel-wise HSI classification. It contains three stages: channel-wise feature extraction network, spatial-wise feature extraction network, and classification network, which are used to extract spectral features, extract spatial features, and generate classification results, respectively. Pyramidal convolutional blocks and polarized attention blocks are combined to extract spectral and spatial features of HSI. Furthermore, residual aggregation and one-shot aggregation are employed to better converge the network. Experimental results on several public HSI datasets demonstrate that the proposed network outperforms other related methods.

In recent years, convolutional neural networks (CNNs) have been introduced for pixel-wise hyperspectral image (HSI) classification tasks. However, some problems of the CNNs are still insufficiently addressed, such as the receptive field problem, small sample problem, and feature fusion problem. To tackle the above problems, we proposed a two-branch convolutional neural network with a polarized full attention mechanism for HSI classification. In the proposed network, two-branch CNNs are implemented to efficiently extract the spectral and spatial features, respectively. The kernel sizes of the convolutional layers are simplified to reduce the complexity of the network. This approach can make the network easier to be trained and fit the network to small sample size conditions. The one-shot connection technique is applied to improve the efficiency of feature extraction. An improved full attention block, named polarized full attention, is exploited to fuse the feature maps and provide global contextual information. Experimental results on several public HSI datasets confirm the effectiveness of the proposed network.

In recent years, hyperspectral image (HSI) classification has become a hot research direction in remote sensing image processing. Benefiting from the development of deep learning, convolutional neural networks (CNNs) have shown extraordinary achievements in HSI classification. Numerous methods combining CNNs and attention mechanisms (AMs) have been proposed for HSI classification. However, to fully mine the features of HSI, some of the previous methods apply dense connections to enhance the feature transfer between each convolution layer. Although dense connections allow these methods to fully extract features in a few training samples, it decreases the model efficiency and increases the computational cost. Furthermore, to balance model performance against complexity, the AMs in these methods compress a large number of channels or spatial resolutions during the training process, which results in a large amount of useful information being discarded. To tackle these issues, in this article, a novel one-shot dense network with polarized attention, namely, OSDN, was proposed for HSI classification. More precisely, since HSI contains rich spectral and spatial information, the OSDN has two independent branches to extract spectral and spatial features, respectively. Similarly, the polarized AMs contain two components: channel-only AMs and spatial-only AMs. Both polarized AMs can use a specially designed filtering method to reduce the complexity of the model while maintaining high internal resolution in both the channel and spatial dimensions. To verify the effectiveness and lightness of OSDN, extensive experiments were carried out on five benchmark HSI datasets, namely, Pavia University (PU), Kennedy Space Center (KSC), Botswana (BS), Houston 2013 (HS), and Salinas Valley (SV). Experimental results consistently showed that the OSDN can greatly reduce computational cost and parameters while maintaining high accuracy in a few training samples.

In recent years, with the continuous advancement of Earth observation technologies, the joint utilization of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) for classifying complex land cover types has garnered widespread attention in the field of multi-source remote sensing. However, the diversity of land cover increases the complexity of the spatial and spectral structures in remote sensing data, creating challenges for extracting discriminative features effectively. Moreover, the heterogeneity of multi-source remote sensing data poses challenges for existing methods to effectively integrate complementary information from various data sources. To address these challenges, a multi-scale split-recombination cooperative fusion network (MSRCFNet) is proposed for joint land cover classification using HSI and LiDAR data. It consists of three main components: multiple parallel multi-scale hierarchical inverted-pyramid (MHIP) modules, a cross-modal cooperative fusion module (CCFM), and a classification module. The MHIP module comprises multiple convolutional split-recombination blocks (CSRBs) at various scales, designed to extract and fuse discriminative multi-scale features. CCFM leverages spatial-scale consistency and the self-attention mechanism to model global relationships between different modalities, and then applies the cross-attention mechanism to effectively integrate complementary information from heterogeneous data. The classification module transforms the fused features into the final classification results. Experimental results on three publicly available HSI-LiDAR datasets demonstrate the superiority of the proposed network over state-of-the-art methods.

Hyperspectral image (HSI) classification is one of the most crucial tasks in remote sensing processing. The attention mechanism is preferable to a convolutional neural network (CNN), due to its superior ability to express information during HSI processing. Recently, numerous methods combining CNNs and attention mechanisms have been applied in HSI classification. However, it remains a challenge to achieve high-accuracy classification by fully extracting effective features from HSIs under the conditions of limited labeled samples. In this paper, we design a novel HSI classification network based on multiscale hybrid networks and attention mechanisms. The network consists of three subnetworks: a spectral-spatial feature extraction network, a spatial inverted pyramid network, and a classification network, which are employed to extract spectral-spatial features, to extract spatial features, and to obtain classification results, respectively. The multiscale fusion network and attention mechanisms complement each other by capturing local and global features separately. In the spatial pyramid network, multiscale spaces are formed through down-sampling, which can reduce redundant information while retaining important information. The structure helps the network better capture spatial features at different scales, and to improve classification accuracy. Experimental results on various public HSI datasets demonstrate that the designed network is extremely competitive compared to current advanced approaches, under the condition of insufficient samples.

With the rapid advancement of deep learning technologies, the use of computers for processing and analyzing multimodal remote sensing data has attracted significant attention. Joint land cover classification (LCC) using hyperspectral image (HSI) and light detection and ranging (LiDAR) data is one such key area of research. Recently, the emerging deep learning framework Mamba has shown superior performance over traditional architectures, including transformers and convolutional neural networks. However, its application to LCC faces challenges. First, existing methods typically use a unified feature extraction approach for heterogeneous data, which fails to capture the distinct characteristics of each data modality. Moreover, effectively integrating these heterogeneous features remains a significant difficulty. To address these issues, we propose the multimodal fusion Mamba network (M2FMNet), which consists of three key components: the spatial–spectral adaptive Mamba, the elevation-enhanced Mamba, and an enhanced fusion module. The spatial–spectral adaptive Mamba combines two distinct scanning methods to efficiently extract spatial and spectral features from HSI data. The elevation-enhanced Mamba, designed for LiDAR data, utilizes a specialized scanning method to extract elevation features. Finally, the enhanced fusion module integrates intra- and intermodal relationships of these features at the pixel level. Experimental results on three real-world datasets show that the M2FMNet outperforms state-of-the-art methods in both qualitative and quantitative metrics.