Convolutional neural network (CNN)-based and Transformer-based methods for hyperspectral image (HSI) classification have rapidly advanced due to their unique characterization capabilities. However, the fixed kernel sizes in convolutional layers limit the comprehensive utilization of multi-scale features in HSI land cover analysis, while the Transformer’s multi-head self-attention (MHSA) mechanism faces challenges in effectively encoding feature information across various dimensions. To tackle this issue, this article introduces an HSI classification method, based on multi-scale convolutional features and multi-attention mechanisms (i.e., MSCF-MAM). Firstly, the model employs a multi-scale convolutional module to capture features across different scales in HSIs. Secondly, to enhance the integration of local and global channel features and establish long-range dependencies, a feature enhancement module based on pyramid squeeze attention (PSA) is employed. Lastly, the model leverages a classical Transformer Encoder (TE) and linear layers to encode and classify the transformed spatial–spectral features. The proposed method is evaluated on three publicly available datasets—Salina Valley (SV), WHU-Hi-HanChuan (HC), and WHU-Hi-HongHu (HH). Extensive experimental results have demonstrated that the MSCF-MAM method outperforms several representative methods in terms of classification performance.

In order to overcome the disadvantages of convolution neural network (CNN) in the current hyperspectral image (HSI) classification/segmentation methods, such as the inability to recognize the rotation of spatial objects, the difficulty to capture the fine spatial features and the problem that principal component analysis (PCA) ignores some important information when it retains few components, in this paper, an HSI segmentation model based on extended multi-morphological attribute profile (EMAP) features and cubic capsule network (EMAP–Cubic-Caps) was proposed. EMAP features can effectively extract various attributes profile features of entities in HSI, and the cubic capsule neural network can effectively capture complex spatial features with more details. Firstly, EMAP algorithm is introduced to extract the morphological attribute profile features of the principal components extracted by PCA, and the EMAP feature map is used as the input of the network. Then, the spectral and spatial low-layer information of the HSI is extracted by a cubic convolution network, and the high-layer information of HSI is extracted by the capsule module, which consists of an initial capsule layer and a digital capsule layer. Through the experimental comparison on three well-known HSI datasets, the superiority of the proposed algorithm in semantic segmentation is validated.

HSI classification is essential for monitoring and analyzing the Earth’s surface, with methods utilizing convolutional neural networks (CNNs) and transformers rapidly gaining prominence and advancing in recent years. However, CNNs are limited by their restricted receptive fields and can only process local information. Although transformers excel at establishing long-range dependencies, they underutilize the spatial information of HSIs. To tackle these challenges, we present the multi-frequency feature enhancement network (DB-MFENet) for HSI classification. First, orthogonal position encoding (OPE) is employed to map image coordinates into a high-dimensional space, which is then combined with corresponding spectral values to compute a multi-frequency feature. Next, the multi-frequency feature is divided into low-frequency and high-frequency components, which are separately enhanced through a dual-branch structure and then fused. Finally, a transformer encoder and a linear layer are employed to encode and classify the enhanced multi-frequency feature. The experimental results demonstrate that our method is efficient and robust for HSIs classification, achieving overall accuracies of 97.05%, 91.92%, 98.72%, and 96.31% on Indian Pines, Salinas, Pavia University, and WHU-Hi-HanChuan datasets, respectively.

Hyperspectral image classification (HSIC) has garnered increasing attention among researchers. While classical networks like convolution neural networks (CNNs) have achieved satisfactory results with the advent of deep learning, they are confined to processing local information. Vision transformers, despite being effective at establishing long-distance dependencies, face challenges in extracting high-representation features for high-dimensional images. In this paper, we present the multiscale efficient attention with enhanced feature transformer (MEA-EFFormer), which is designed for the efficient extraction of spectral–spatial features, leading to effective classification. MEA-EFFormer employs a multiscale efficient attention feature extraction module to initially extract 3D convolution features and applies effective channel attention to refine spectral information. Following this, 2D convolution features are extracted and integrated with local binary pattern (LBP) spatial information to augment their representation. Then, the processed features are fed into a spectral–spatial enhancement attention (SSEA) module that facilitates interactive enhancement of spectral–spatial information across the three dimensions. Finally, these features undergo classification through a transformer encoder. We evaluate MEA-EFFormer against several state-of-the-art methods on three datasets and demonstrate its outstanding HSIC performance.