Substantial deep learning methods have been utilized for hyperspectral image (HSI) classification recently. Vision Transformer (ViT) is skilled in modeling the overall structure of images and has been introduced to HSI classification task. However, the fixed patch division operation in ViT may lead to insufficient feature extraction, especially the features of the edges between patches will be ignored. To address this problem, we devise a workflow for HSI classification based on the Nested Transformers (NesT). The NesT employs the block aggregation module to extract edge information between patches, which realizes cross-block communication of nonlocal information and optimizes global information extraction. In this paper, the NesT is used for HSI classification for the first time. The experiments are carried out on four widely used hyperspectral datasets: Indian Pines, Salinas, Tea Farm, and Xiongan New Area (Matiwan Village). The obtained results reveal that the NesT can provide competitive results compared to conventional machine learning and deep learning methods and achieve top accuracy on four datasets, which proves the superiority of the NesT in HSI classification with limited training samples.

Deep learning methods have shown great promise in automatically extracting features from hyperspectral images (HSIs) for classification purposes. Recently, researchers have recognized the importance of high-order feature interactionscapturing relationships between features in different image regions-in extracting discriminative features. Despite their effectiveness, the existing deep learning models for HSI classification often overlook high-order feature interactions, resulting in suboptimal performance. To address this issue, we propose a novel spectral-spatial multiorder interaction network (S 2 MoINet) for HSI classification. The proposed framework can effectively extract highly discriminative features by leveraging correlations between features in different locations, significantly improving the classification accuracy. More specifically, we design a multiorder spectralspatial interaction block in the framework to extract the high-order and generalized features by leveraging the interaction between spatial and spectral features. Based on experimental results from four public HSI datasets, it has been shown that the proposed S 2 MoINet delivers optimal classification results when compared to other state-of-the-art methods.

The classification of hyperspectral remote sensing images (HSI) is an important task in the processing and application of hyperspectral images. Convolutional neural network (CNN) has significant advantages in the extraction and fusion of hyperspectral image spectrum and spatial features, so it has become a common method in the field of HSI classification. However, the spectral domain feature redundancy of hyperspectral images is very high, and the spatial domain feature structure is complex, which makes CNN more time-consuming and higher memory requirements in the feature extraction process. Based on this problem, lightweight networks with fewer parameters have gradually become the main application method in the field of HSI classification. In order to reduce the computational complexity of deep feature extraction and take into account the shallow features, a high-order nonlinear Ghost module is proposed on the basis of the original Ghost linear transformation module. Furthermore, in view of the independent characteristics of each dimension of HSI, a Trip-GhostNet is proposed, which simultaneously extracts and fuses features from three dimensions in a lightweight manner. According to the distribution characteristics of HSI, the influence of attention embedding methods in the high-order Ghost module of each branch on the feature extraction is compared and analyzed. The results show that the proposed model can reduce model calculations and improve classification accuracy, and is suitable for HSI classification problems.

No abstract