Hyperspectral Image Classification Tasks Research Articles

DMAF-NET: Deep Multi-Scale Attention Fusion Network for Hyperspectral Image Classification with Limited Samples

In recent years, deep learning methods have achieved remarkable success in hyperspectral image classification (HSIC), and the utilization of convolutional neural networks (CNNs) has proven to be highly effective. However, there are still several critical issues that need to be addressed in the HSIC task, such as the lack of labeled training samples, which constrains the classification accuracy and generalization ability of CNNs. To address this problem, a deep multi-scale attention fusion network (DMAF-NET) is proposed in this paper. This network is based on multi-scale features and fully exploits the deep features of samples from multiple levels and different perspectives with an aim to enhance HSIC results using limited samples. The innovation of this article is mainly reflected in three aspects: Firstly, a novel baseline network for multi-scale feature extraction is designed with a pyramid structure and densely connected 3D octave convolutional network enabling the extraction of deep-level information from features at different granularities. Secondly, a multi-scale spatial–spectral attention module and a pyramidal multi-scale channel attention module are designed, respectively. This allows modeling of the comprehensive dependencies of coordinates and directions, local and global, in four dimensions. Finally, a multi-attention fusion module is designed to effectively combine feature mappings extracted from multiple branches. Extensive experiments on four popular datasets demonstrate that the proposed method can achieve high classification accuracy even with fewer labeled samples.

Spectral Spatial Neighborhood Attention Transformer for Hyperspectral Image Classification

Hyperspectral image (HSI) can provide rich spectral information, which can be helpful for accurate classification in many applications. However, the hyperspectral image classification task has challenges, including limited labeled data, data redundancy, data sparsity, and imbalanced class samples. Over time, various methods have been proposed to solve the above-mentioned problems. To mitigate the issue mentioned above in this paper, we present the neighborhood attention transformer with a channel-wise shift technique for hyperspectral image classification. The neighborhood attention transformer leverages the power of the attention mechanism to capture the spatial relationship between neighboring pixels and extract discriminative features. The channel-wise shift techniques empower the model to adjust the spectral characteristics of each channel adaptively, enhancing its ability to handle the spectral variations present in hyperspectral data. To validate the effectiveness of the proposed model, we conduct comprehensive experiments on the publically available dataset. The results demonstrate that our model consistently outperforms other state-of-the-art methods. The overall accuracy of the proposed model reached 99.41 % , 99.93 % , 98.35 % 99.59 % four datasets.

Semi-Supervised Multiscale Dynamic Graph Convolution Network for Hyperspectral Image Classification.

In recent years, convolutional neural networks (CNNs)-based methods achieve cracking performance on hyperspectral image (HSI) classification tasks, due to its hierarchical structure and strong nonlinear fitting capacity. Most of them, however, are supervised approaches that need a large number of labeled data to train them. Conventional convolution kernels are fixed shape of rectangular with fixed sizes, which are good at capturing short-range relations between pixels within HSIs but ignore the long-range context within HSIs, limiting their performance. To overcome the limitations mentioned above, we present a dynamic multiscale graph convolutional network (GCN) classifier (DMSGer). DMSGer first constructs a relatively small graph at region-level based on a superpixel segmentation algorithm and metric-learning. A dynamic pixel-level feature update strategy is then applied to the region-level adjacency matrix, which can help DMSGer learn the pixel representation dynamically. Finally, to deeply understand the complex contents within HSIs, our model is expanded into a multiscale version. On the one hand, by introducing graph learning theory, DMSGer accomplishes HSI classification tasks in a semi-supervised manner, relieving the pressure of collecting abundant labeled samples. Superpixels are generally in irregular shapes and sizes which can group only similar pixels in a neighborhood. On the other hand, based on the proposed dynamic-GCN, the pixel-level and region-level information can be captured simultaneously in one graph convolution layer such that the classification results can be improved. Also, due to the proper multiscale expansion, more helpful information can be captured from HSIs. Extensive experiments were conducted on four public HSIs, and the promising results illustrate that our DMSGer is robust in classifying HSIs. Our source codes are available at https://github.com/TangXu-Group/DMSGer.

A fast hypergraph neural network with detail preservation for hyperspectral image classification

ABSTRACT Hypergraph neural networks (HGNNs), extending the techniques of graph neural networks, have been applied to various fields due to their ability to capture more complex high-order node relationships. However, for hyperspectral image (HSI) classification tasks, previous HGNN-based works usually constructed hypergraphs using pixels as nodes, resulting in massive computational costs. Meanwhile, pixel-level personalized features are required for HSI classification. To achieve high efficiency and accuracy simultaneously, this paper presents a fast hypergraph neural network with detail preservation (DPFHNet) for HSI classification. It constructs hypergraphs at the superpixel level to reduce time consumption and supplement pixel-level detail features through a classification refinement module. This framework contains multiple stages. Firstly, its main stage is designed with HGNNs from a superpixel viewpoint rather than pixels, providing a fast strategy to capture high-order complex relationships of multiple homogeneous irregular regions. After that, auxiliary stages based on convolutional neural networks are integrated into the main stage, which adopts a hierarchical design and attempts to acquire pixel-level spatial-spectral information before the hypergraph feature extraction of the main stage, assisting in learning more valuable features. Finally, a classification refinement module is constructed, which generates pixel-level detail features to refine the superpixel-level features obtained by HGNN. Experiments on three datasets illustrate that DPFHNet achieves competitive results and efficiency compared to advanced methodologies.

Hyperspectral Image Classification Based on 3D–2D Hybrid Convolution and Graph Attention Mechanism

Convolutional neural networks and graph convolutional neural networks are two classical deep learning models that have been widely used in hyperspectral image classification tasks with remarkable achievements. However, hyperspectral image classification models based on graph convolutional neural networks using only shallow spectral or spatial features are insufficient to provide reliable similarity measures for constructing graph structures, limiting their classification performance. To address this problem, we propose a new end-to-end hyperspectral image classification model combining 3D–2D hybrid convolution and a graph attention mechanism (3D–2D-GAT). The model utilizes the collaborative work of hybrid convolutional feature extraction module and GAT module to improve classification accuracy. First, a 3D–2D hybrid convolutional network is constructed and used to quickly extract the discriminant deep spatial-spectral features of various ground objects in hyperspectral image. Then, the graph is built based on deep spatial-spectral features to enhance the feature representation ability. Finally, a network of graph attention mechanism is adopted to learn long-range spatial relationship and distinguish the intra-class variation and inter-class similarity among different samples. The experimental results on three datasets, Indian Pine, the University of Pavia and Salinas Valley show that the proposed method can achieve higher classification accuracy compared with other advanced methods.

S[formula omitted]WaveNet: A novel spectral–spatial wave network for hyperspectral image classification

Deep learning has made significant progress in hyperspectral image (HSI) classification, and its powerful ability to automatically learn abstract features is well recognized. Recently, the simple architecture of multi-layer perceptron (MLP) has been extensively employed to extract long-range dependencies of HSI and achieved impressive results. However, existing MLP-based models exhibit insufficient representation of spectral–spatial information in HSI and generally aggregate features with fixed weights, which limits their ability to capture semantic differences. To tackle these challenges, this paper proposes a novel spectral–spatial wave network (S2WaveNet) for HSI classification tasks to enhance the representation capability of spectral–spatial features in ground objects. Specifically, the spectral–spatial wave mixer (S2WaveMixer) block is designed as a key component to represent each HSI input as a wave function with amplitude and phase parts. Thus, it enables a deeper dynamic perception and facilitates the extraction of spectral–spatial feature variations of ground objects. The amplitude represents the original features and the phase term is a complex value changing based on the semantic contents of the input images. Furthermore, the inception unit is introduced into the S2WaveMixer block to consider spectral–spatial information at multiple granularity levels. Experiments conducted on five public datasets demonstrate the superiority of S2WaveNet in classification performance and generalization compared to competitors.

Robust Self-Ensembling Network for Hyperspectral Image Classification.

Recent research has shown the great potential of deep learning algorithms in the hyperspectral image (HSI) classification task. Nevertheless, training these models usually requires a large amount of labeled data. Since the collection of pixel-level annotations for HSI is laborious and time-consuming, developing algorithms that can yield good performance in the small sample size situation is of great significance. In this study, we propose a robust self-ensembling network (RSEN) to address this problem. The proposed RSEN consists of two subnetworks including a base network and an ensemble network. With the constraint of both the supervised loss from the labeled data and the unsupervised loss from the unlabeled data, the base network and the ensemble network can learn from each other, achieving the self-ensembling mechanism. To the best of our knowledge, the proposed method is the first attempt to introduce the self-ensembling technique into the HSI classification task, which provides a different view on how to utilize the unlabeled data in HSI to assist the network training. We further propose a novel consistency filter to increase the robustness of self-ensembling learning. Extensive experiments on three benchmark HSI datasets demonstrate that the proposed algorithm can yield competitive performance compared with the state-of-the-art methods.

DCTransformer: A Channel Attention Combined Discrete Cosine Transform to Extract Spatial–Spectral Feature for Hyperspectral Image Classification

Hyperspectral image (HSI) classification tasks have been adopted in huge applications of remote sensing recently. With the rise of deep learning development, it becomes crucial to investigate how to exploit spatial–spectral features. The traditional approach is to stack models that can encode spatial–spectral features, coupling sufficient information as much as possible, before the classification model. However, this sequential stacking tends to cause information redundancy. In this paper, a novel network utilizing the channel attention combined discrete cosine transform (DCTransformer) to extract spatial–spectral features has been proposed to address this issue. It consists of a detail spatial feature extractor (DFE) with CNN blocks and a base spectral feature extractor (BFE) utilizing the channel attention mechanism (CAM) with a discrete cosine transform (DCT). Firstly, the DFE can extract detailed context information using a series of layers of a CNN. Further, the BFE captures spectral features using channel attention and stores the wider frequency information by utilizing the DCT. Ultimately, the dynamic fusion mechanism has been adopted to fuse the detail and base features. Comprehensive experiments show that the DCTransformer achieves a state-of-the-art (SOTA) performance in the HSI classification task, compared to other methods on four datasets, the University of Houston (UH), Indian Pines (IP), MUUFL, and Trento datasets. On the UH dataset, the DCTransformer achieves an OA of 94.40%, AA of 94.89%, and kappa of 93.92.

Dual-input ultralight multi-head self-attention learning network for hyperspectral image classification

ABSTRACT In the hyperspectral image (HSI) classification tasks, various deep learning models have achieved remarkable success. However, most deep learning models are compute-intensive, requiring significant computing power, time, and other resources. It becomes a challenge to pursue better results while saving computational resources. Therefore, a novel dual-input ultralight multi-head self-attention learning network (DUMS-LN) is proposed for HSI classification. The proposed DUMS-LN consists of three main core modules, namely the high-dimensional reduced module (HDRM), lightweight multi-head self-attention (LMHSA) module, and linearized hierarchical conversion module (LHCM). HDRM is used as a pre-processing module with efficient data compression and combines spatial and spectral information extraction from the raw data to provide cleaner and more comprehensive feature data for subsequent processing. In addition, the core computational module of DUMS-LN is the LMHSA module, which is lightweight but possesses better data processing capability than the traditional multi-head self-attention module. Finally, the LHCM divides the model into two phases, reducing the dimensionality of the feature data phase by phase so that the LMHSA module can perform feature extraction at different levels. Experiments on four benchmark HSI datasets show that the proposed DUMS-LN outperforms the comparison HSI classification algorithms regarding speed and classification accuracy.

SemanticFormer: Hyperspectral image classification via semantic transformer

Hyperspectral image (HSI) classification is an active research problem in computer vision and multimedia field. Contrary to traditional image data, HSIs contain rich spectral, spatial and semantic information. Thus, how to extract the discriminative features for HSIs by integrating spectral, spatial and semantic cues together is the core issue to address HSI classification task. Existing works mainly focus on exploring spectral and spatial information which usually fail to fully explore the rich semantic information in HSIs. To address this issue, in this paper, we first propose a novel semantic Transformer scheme, named SemanticFormer, which aims to learn discriminative visual representations for semantics by exploiting the interaction among different semantic tokens. Using the proposed SemanticFormer, we then propose a novel heterogeneous network that contains both spectral–spatial convolution network branch and SemanticFormer branch to extract spectral–spatial and semantic features simultaneously for HSIs. Experiments on two widely used datasets demonstrate the effectiveness of our SemanticFormer and HSI classification network method. Our codes will be available in https://github.com/SissiW/SemanticFormer.

Achieving Better Category Separability for Hyperspectral Image Classification: A Spatial-Spectral Approach.

The task of hyperspectral image (HSI) classification has attracted extensive attention. The rich spectral information in HSIs not only provides more detailed information but also brings a lot of redundant information. Redundant information makes spectral curves of different categories have similar trends, which leads to poor category separability. In this article, we achieve better category separability from the perspective of increasing the difference between categories and reducing the variation within category, thus improving the classification accuracy. Specifically, we propose the template spectrum-based processing module from spectral perspective, which can effectively expose the unique characteristics of different categories and reduce the difficulty of model mining key features. Second, we design an adaptive dual attention network from spatial perspective, where the target pixel can adaptively aggregate high-level features by evaluating the confidence of effective information in different receptive fields. Compared with the single adjacency scheme, the adaptive dual attention mechanism makes the ability of target pixel to combine spatial information to reduce variation more stable. Finally, we designed a dispersion loss from the classifier's perspective. By supervising the learnable parameters of the final classification layer, the loss makes the category standard eigenvectors learned by the model more dispersed, which improves the category separability and reduces the rate of misclassification. Experiments on three common datasets show that our proposed method is superior to the comparison method.

HKNAS: Classification of Hyperspectral Imagery Based on Hyper Kernel Neural Architecture Search.

Recent neural architecture search (NAS)-based approaches have made great progress in the hyperspectral image (HSI) classification tasks. However, the architectures are usually optimized independently of the network weights, increasing searching time, and restricting model performances. To tackle these issues, in this article, different from previous methods that extra define structural parameters, we propose to directly generate structural parameters by utilizing the specifically designed hyper kernels, ingeniously converting the original complex dual optimization problem into easily implemented one-tier optimizations, and greatly shrinking searching costs. Then, we develop a hierarchical multimodule search space whose candidate operations only contain convolutions, and these operations can be integrated into unified kernels. Using the above searching strategy and searching space, we obtain three kinds of networks to separately conduct pixel-level or image-level classifications with 1-D or 3-D convolutions. In addition, by combining the proposed hyper kernel searching scheme with the 3-D convolution decomposition mechanism, we obtain diverse architectures to simulate 3-D convolutions, greatly improving network flexibilities. A series of quantitative and qualitative experiments on six public datasets demonstrate that the proposed methods achieve state-of-the-art results compared with other advanced NAS-based HSI classification approaches.

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification Using Enhanced Transformer with Large-Kernel Attention

In the hyperspectral image (HSI) classification task, every HSI pixel is labeled as a specific land cover category. Although convolutional neural network (CNN)-based HSI classification methods have made significant progress in enhancing classification performance in recent years, they still have limitations in acquiring deep semantic features and face the challenges of escalating computational costs with increasing network depth. In contrast, the Transformer framework excels in expressing high-level semantic features. This study introduces a novel classification network by extracting spectral–spatial features with an enhanced Transformer with Large-Kernel Attention (ETLKA). Specifically, it utilizes distinct branches of three-dimensional and two-dimensional convolutional layers to extract more diverse shallow spectral–spatial features. Additionally, a Large-Kernel Attention mechanism is incorporated and applied before the Transformer encoder to enhance feature extraction, augment comprehension of input data, reduce the impact of redundant information, and enhance the model’s robustness. Subsequently, the obtained features are input to the Transformer encoder module for feature representation and learning. Finally, a linear layer is employed to identify the first learnable token for sample label acquisition. Empirical validation confirms the outstanding classification performance of ETLKA, surpassing several advanced techniques currently in use. This research provides a robust and academically rigorous solution for HSI classification tasks, promising significant contributions in practical applications.

QTN: Quaternion Transformer Network for Hyperspectral Image Classification

Numerous state-of-the-art transformer-based techniques with self-attention mechanisms have recently been demonstrated to be quite effective in the classification of hyperspectral images (HSIs). However, traditional transformer-based methods severely suffer from the following problems when processing HSIs with three dimensions: (1) processing the HSIs using 1D sequences misses the 3D structure information; (2) too expensive numerous parameters for hyperspectral image classification tasks; (3) only capturing spatial information while lacking the spectral information. To solve these problems, we propose a novel Quaternion Transformer Network (QTN) for recovering self-adaptive and long-range correlations in HSIs. Specially, we first develop a band adaptive selection module (BASM) for producing Quaternion data from HSIs. And then, we propose a new and novel quaternion self-attention (QSA) mechanism to capture the local and global representations. Finally, we propose a new and novel transformer method, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., QTN by stacking a series of QSA for hyperspectral classification. The proposed QTN could exploit computation using Quaternion algebra in hypercomplex spaces. Extensive experiments on three public datasets demonstrate that the QTN outperforms the state-of-the-art vision transformers and convolution neural networks.

Hyperspectral Image Classification Promotion Using Dynamic Convolution Based on Structural Re-Parameterization

In a hyperspectral image classification (HSIC) task, manually labeling samples requires a lot of manpower and material resources. Therefore, it is of great significance to use small samples to achieve the HSIC task. Recently, convolutional neural networks (CNNs) have shown remarkable performance in HSIC, but they still have some areas for improvement. (1) Convolutional kernel weights are determined through initialization and cannot be adaptively adjusted based on the input data. Therefore, it is difficult to adaptively learn the structural features of the input data. (2) The convolutional kernel size is single per layer, which leads to the loss of local information for a large convolutional kernel or global information for a small convolutional kernel. In order to solve the above problems, we propose a plug-and-play method called dynamic convolution based on structural re-parameterization (DCSRP). The contributions of this method are as follows. Firstly, compared with traditional convolution, dynamic convolution is a non-linear function, so it has more representation power. In addition, it can adaptively capture the contextual information of input data. Secondly, the large convolutional kernel and the small convolutional kernel are integrated into a new large convolutional kernel. The large convolutional kernel shares the advantages of the two convolution kernels, which can capture global information and local information at the same time. The results in three publicly available HSIC datasets show the effectiveness of the DCSRP.

A multi-range spectral-spatial transformer for hyperspectral image classification

In recent years, the transformer-based approach becoming a hot research topic in hyperspectral image (HSI) classification tasks. However, most of these studies have focused on optimizing the model framework in pursuit of high-accuracy classification, with little attention to the composition of the input token sequence as an important factor affecting the performance of the transformer. Therefore, this paper further explores a novel token structure to strengthen the Transformer's performance for HSI classification tasks, based on which a Multi-Range Spectral-Spatial Transformer (MRSST) framework is developed. Specifically, a convolutional feature pre-encoder with two branches is designed to extract shallow features for each spectral channel separately. Then, a token generator is introduced to combine the shallow features with the raw spectral information to yield the token sequences with multi-range information. Finally, the tokens are input into the transformer encoders enhanced by a module that strengthens the information exchange between its mid-range and short-range semantic features. Experiments conducted on three well-known hyperspectral datasets demonstrate that the proposed multi-range composite token sequences and information exchange mechanisms significantly enhance the transformer's performance. Codes are released at: https://github.com/HyperSystemAndImageProc/Multi-Range-Spectral-Spatial-Transformer.

S2Former: Parallel Spectral–Spatial Transformer for Hyperspectral Image Classification

Due to their excellent representation talent in local features, the convolutional neural network (CNN) has achieved favourable performance in hyperspectral image (HSI) classification tasks. Nevertheless, current CNN models exhibit a marked flaw: they are hard to model the dependencies in long-range distanced positions. This flaw becomes more problematic for the HSI classification task, which targets extracting more discriminative features in local and global dimensions from limited samples. In this paper, we introduce a spatial–spectral transformer (S2Former), which explores spatial and spectral feature extraction in a dual-stream framework for HSI Classification. S2Former, which consists of a spatial transformer and a spectral transformer in parallel branches, extracts the discriminative feature in spatial and spectral dimensions. More specifically, we propose multi-head spatial self-attention to capture the long-range spatial dependency of non-adjacent HSI pixels in a spatial transformer. In the spectral transformer, we propose multi-head covariance spectral attention to mine and represent spectral signatures by computing covariance-based channel maps. Meanwhile, the local activation feed-forward network is developed to complement local details. Extensive experiments conducted on four publicly available datasets indicate that our S2Former achieves state-of-the-art performance for the HSI classification task.

Attack-invariant attention feature for adversarial defense in hyperspectral image classification

Although deep neural networks (DNNs) have achieved excellent performance on hyperspectral image (HSI) classification tasks, their robustness is threatened by carefully created adversarial examples. Therefore, adversarial defense methods have provided an effective defense strategy to protect HSI classification networks. However, most defense models are highly dependent on known types of adversarial examples, which leads to poor generalization to defend against unknown attacks. In this study, we propose an attack-invariant attention feature-based defense (AIAF-Defense) model to improve the generalization ability of the defense model. Specifically, the AIAF-Defense model has an encoder–decoder structure to remove the perturbations from the HSI adversarial examples. We design a feature-disentanglement network as the encoder structure to decouple the attack-invariant spectral–spatial feature and attack-variant feature in the adversarial example and apply a decoder structure to reconstruct the legitimate HSI example. In addition, an attention-guided reconstruction loss is proposed to address the attention-shift problem caused by perturbation and provide an attention constraint for the extraction of attack-invariant attention features. Extensive experiments are conducted on three benchmark hyperspectral image datasets, the PaviaU, HoustonU 2018, and Salinas datasets, and the obtained results show that the proposed AIAF-Defense model improves the defense ability on both known and unknown adversarial attacks. The code is available at https://github.com/AAAA-CS/AIAF_HyperspectralAdversarialDefense.

Incorporating Attention Mechanism, Dense Connection Blocks, and Multi-Scale Reconstruction Networks for Open-Set Hyperspectral Image Classification

Hyperspectral image classification plays a crucial role in various remote sensing applications. However, existing methods often struggle with the challenge of unknown classes, leading to decreased classification accuracy and limited generalization. In this paper, we propose a novel deep learning framework called IADMRN, which addresses the issue of unknown class handling in hyperspectral image classification. IADMRN combines the strengths of dense connection blocks and attention mechanisms to extract discriminative features from hyperspectral data. Furthermore, it employs a multi-scale deconvolution image reconstruction sub-network to enhance feature reconstruction and provide additional information for classification. To handle unknown classes, IADMRN utilizes an extreme value theory-based model to calculate the probability of unknown class membership. Experimental results on the three public datasets demonstrate that IADMRN outperforms state-of-the-art methods in terms of classification accuracy for both known and unknown classes. Experimental results show that the proposed methods outperform several state-of-the-art methods, which outperformed DCFSL by 8.47%, 6.57%, and 4.25%, and outperformed MDL4OW by 4.35%, 4.08%, and 2.47% on the Salinas, University of Pavia, and Indian Pines datasets, respectively. The proposed framework is computationally efficient and showcases the ability to effectively handle unknown classes in hyperspectral image classification tasks. Overall, IADMRN offers a promising solution for accurate and robust hyperspectral image classification, making it a valuable tool for remote sensing applications.

Multiscale Pixel-Level and Superpixel-Level Method for Hyperspectral Image Classification: Adaptive Attention and Parallel Multi-Hop Graph Convolution

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have led to promising advancements in hyperspectral image (HSI) classification; however, traditional CNNs with fixed square convolution kernels are insufficiently flexible to handle irregular structures. Similarly, GCNs that employ superpixel nodes instead of pixel nodes may overlook pixel-level features; both networks tend to extract features locally and cause loss of multilayer contextual semantic information during feature extraction due to the fixed kernel. To leverage the strengths of CNNs and GCNs, we propose a multiscale pixel-level and superpixel-level (MPAS)-based HSI classification method. The network consists of two sub-networks for extracting multi-level information of HSIs: a multi-scale hybrid spectral–spatial attention convolution branch (HSSAC) and a parallel multi-hop graph convolution branch (MGCN). HSSAC comprehensively captures pixel-level features with different kernel sizes through parallel multi-scale convolution and cross-path fusion to reduce the semantic information loss caused by fixed convolution kernels during feature extraction and learns adjustable weights from the adaptive spectral–spatial attention module (SSAM) to capture pixel-level feature correlations with less computation. MGCN can systematically aggregate multi-hop contextual information to better model HSIs’ spatial background structure using the relationship between parallel multi-hop graph transformation nodes. The proposed MPAS effectively captures multi-layer contextual semantic features by leveraging pixel-level and superpixel-level spectral–spatial information, which improves the performance of the HSI classification task while ensuring computational efficiency. Extensive evaluation experiments on three real-world HSI datasets demonstrate that MPAS outperforms other state-of-the-art networks, demonstrating its superior feature learning capabilities.