Spectral-spatial Features Research Articles

HTD-TS3: Weakly Supervised Hyperspectral Target Detection Based on Transformer via Spectral-Spatial Similarity.

As an advanced technique in remote sensing, hyperspectral target detection (HTD) is widely concerned in civilian and military applications. However, the limitation of prior and heterogeneous backgrounds makes HTD models sensitive to data corruption under various interference from the environment. In this article, a novel united HTD framework based on the concept of transformer is proposed to extract [HTD based on transformer via spectral-spatial similarity (HTD-TS3)] under weak supervision, which opens up more flexible ways to study HTD. For the first time, the transformer mechanism is introduced into the HTD task to extract spectral and spatial features in a unified optimization procedure. By modeling long-range dependence among spectra, it realizes spectral-spatial joint inference based on long-range context, which addresses the issues of insufficient utilization of spatial information. To provide samples for weakly supervised learning (WSL), the coarse sample selection and spectral sequence construction in an efficient way are proposed, which makes full use of limited prior information. Finally, an exponential constrained nonlinear function is adopted to acquire pixel-level prediction via combining discriminative spectral-spatial features and coarse spatial information. Experiments on real hyperspectral images (HSIs) captured by different sensors at various scenes verify the effectiveness and efficiency of HTD-TS3.

A Variable-Iterative Fully Convolutional Neural Network for Sparse Unmixing

Neural networks have greatly promoted the development of hyperspectral unmixing (HU). Most data-driven deep networks extract features of hyperspectral images (HSIs) by stacking convolutional layers to achieve endmember extraction and abundance estimation. Some model-driven networks have strong interpretability but fail to mine the deep feature. We propose a variable-iterative fully convolutional neural network (VIFCNN) for sparse unmixing, combining the characteristics of these two networks. Under the model-driven iterative framework guided by sparse unmixing by variable splitting and augmented lagrangian (SUnSAL), a data-driven spatial-spectral feature learning module and a spatial information updating module are introduced to enhance the learning of data information. Experimental results on synthetic and real datasets show that VIFCNN significantly outperforms several traditional unmixing methods and two deep learning???based methods. On real datasets, our method improves signal-to-reconstruction error by 17.38%, reduces abundance root-mean-square error by 25.24%, and reduces abundance spectral angle distance by 31.40% compared with U-ADMM-ßUNet.

Spatial-Spectral Middle Cross-Attention Fusion Network for Hyperspectral Image Superresolution

The spatial and spectral features of hyperspectral images exhibit complementarity, and neglecting them prevents the full exploitation of useful information for superresolution. This article proposes a spatial-spectral middle cross-attention fusion network to explore the spatial-spectral structure correlation. Initially, we learn spatial and spectral features through spatial and spectral branches instead of single ones to reduce information compression. Then, a novel middle-cross attention fusion block that includes middle features fusion strategy and cross-attention is proposed to fuse spatial-spectral features to enhance their mutual effects, which aims to explore the spatial-spectral structural correlations. Finally, we propose a spectral feature compensation mechanism to provide complementary information for adjacent band groups. The experimental results show that the proposed method outperforms state-of-the-art algorithms in object values and visual quality.

Center-Highlighted Multiscale CNN for Classification of Hyperspectral Images

Hyperspectral images (HSIs) capture a wide range of spectral features across multiple bands of light, from visible to near-infrared. Hyperspectral image classification technology enables researchers to accurately identify and analyze the composition and distribution of surface materials. Current mainstream deep learning methods typically use block sampling to capture spatial features for the model. However, this approach can affect classification results due to the influence of neighboring features within the sample block. To improve the model’s focus on the center of the sampling block, this study proposes a center highlight with multiscale CNN for hyperspectral image classification (CHMSC). The network utilizes an automatic channel selector (Auto-CHS) to fully consider every channel feature and capture the correlation between the channels. Then, CHMSC enhances the model’s ability to concentrate on the central features of the sampling block utilizing structures such as the center highlight. Finally, before outputting the prediction results, an SENet is employed to further refine the features and learn associate interactions between different scales of spatial features and spectral features. Experimental results from three hyperspectral datasets validate the effectiveness of the proposed method. Specifically, when 15 samples from each class are selected for training, CHMSC achieves the highest overall accuracy (OA) of 90.05%, 92.78%, and 90.15% on the three datasets, outperforming other methods with increases of more than 3.11%, 1.8%, and 2.01% in OA, respectively.

Bidirectional Mamba with Dual-Branch Feature Extraction for Hyperspectral Image Classification

The hyperspectral image (HSI) classification task is widely used in remote sensing image analysis. The HSI classification methods based on convolutional neural networks (CNNs) have greatly improved the classification performance. However, they cannot well utilize the sequential properties of spectral features and face the challenge of increasing computational cost with the increase in network depth. To address these shortcomings, this paper proposes a novel network with a CNN-Mamba architecture, called DBMamba, which uses a bidirectional Mamba to process spectral feature sequences at a linear computational cost. In the DBMamba, principal component analysis (PCA) is first used to extract the main features of the data. Then, a dual-branch CNN structure, with the fused features from spectral–spatial features by 3D-CNN and spatial features by 2D-CNN, is used to extract shallow spectral–spatial features. Finally, a bidirectional Mamba is used to effectively capture global contextual information in features and significantly enhance the extraction of spectral features. Experimental results on the Indian Pines, Salinas, and Pavia University datasets demonstrate that the classification performance surpasses that of many cutting-edge methods, improving by 1.04%, 0.15%, and 0.09%, respectively, over the competing SSFTT method. The research in this paper enhances the existing knowledge on HSI classification and provides valuable insights for future research in this field.

Capsule Attention Network for Hyperspectral Image Classification

While many neural networks have been proposed for hyperspectral image classification, current backbones cannot achieve accurate results due to the insufficient representation by scalar features and always cause a cumbersome calculation burden. To solve the problem, we propose the capsule attention network (CAN), which combines an activity vector with an attention mechanism to improve HSI classification. In particular, we consider two attention mechanisms to improve the effectiveness of the activity vectors. First, an attention-based feature extraction (AFE) module is proposed to preprocess the spectral-spatial features of HSI data, which effectively mines useful information before the generation of the activity vectors. Second, we propose a self-weighted mechanism (SWM) to distinguish the importance of different capsule convolutions, which enhances the representation of the primary activity vectors. Experiments on four well-known HSI datasets have shown our CAN surpasses state-of-the-art (SOTA) methods on three widely used metrics with a much lower computational burden.

GASSF-Net: Geometric Algebra Based Spectral-Spatial Hierarchical Fusion Network for Hyperspectral and LiDAR Image Classification

The field of multi-source remote sensing observation is becoming increasingly dynamic through the integration of various remote sensing data sources. However, existing deep learning methods face challenges in differentiating between internal and external relationships and capturing fine spatial features. These models often struggle to effectively capture comprehensive information across remote sensing data bands, and they have inherent differences in the size, structure, and physical properties of different remote sensing datasets. To address these challenges, this paper proposes a novel geometric-algebra-based spectral–spatial hierarchical fusion network (GASSF-Net), which uses geometric algebra for the first time to process multi-source remote sensing images, enabling a more holistic approach to handling these images by simultaneously leveraging the real and imaginary components of geometric algebra to express structural information. This method captures the internal and external relationships between remote sensing image features and spatial information, effectively fusing the features of different remote sensing data to improve classification accuracy. GASSF-Net uses geometric algebra (GA) to represent pixels from different bands as multivectors, thus capturing the intrinsic relationships between spectral bands while preserving spatial information. The network begins by deeply mining the spectral–spatial features of a hyperspectral image (HSI) using pairwise covariance operators. These features are then extracted through two branches: a geometric-algebra-based branch and a real-valued network branch. Additionally, the geometric-algebra-based network extracts spatial information from light detection and ranging (LiDAR) to complement the elevation data lacking in the HSI. Finally, a genetic-algorithm-based cross-fusion module is introduced to fuse the HSI and LiDAR data for improved classification. Experiments conducted on three well-known datasets, Trento, MUUFL, and Houston, demonstrate that GASSF-Net significantly outperforms traditional methods in terms of classification accuracy and model efficiency.

GroupFormer for hyperspectral image classification through group attention

Hyperspectral image (HSI) data has a wide range of valuable spectral information for numerous tasks. HSI data encounters challenges such as small training samples, scarcity, and redundant information. Researchers have introduced various research works to address these challenges. Convolution Neural Network (CNN) has gained significant success in the field of HSI classification. CNN’s primary focus is to extract low-level features from HSI data, and it has a limited ability to detect long-range dependencies due to the confined filter size. In contrast, vision transformers exhibit great success in the HSI classification field due to the use of attention mechanisms to learn the long-range dependencies. As mentioned earlier, the primary issue with these models is that they require sufficient labeled training data. To address this challenge, we proposed a spectral-spatial feature extractor group attention transformer that consists of a multiscale feature extractor to extract low-level or shallow features. For high-level semantic feature extraction, we proposed a group attention mechanism. Our proposed model is evaluated using four publicly available HSI datasets, which are Indian Pines, Pavia University, Salinas, and the KSC dataset. Our proposed approach achieved the best classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa coefficient. As mentioned earlier, the proposed approach utilized only 5%, 1%, 1%, and 10% of the training samples from the publicly available four datasets.

Multistage Spatial-Spectral Fusion Network for Spectral Super-Resolution.

Spectral super-resolution (SSR) aims to restore a hyperspectral image (HSI) from a single RGB image, in which deep learning has shown impressive performance. However, the majority of the existing deep-learning-based SSR methods inadequately address the modeling of spatial-spectral features in HSI. That is to say, they only sufficiently capture either the spatial correlations or the spectral self-similarity, which results in a loss of discriminative spatial-spectral features and hence limits the fidelity of the reconstructed HSI. To solve this issue, we propose a novel SSR network dubbed multistage spatial-spectral fusion network (MSFN). From the perspective of network design, we build a multistage Unet-like architecture that differentially captures the multiscale features of HSI both spatialwisely and spectralwisely. It consists of two types of the self-attention mechanism, which enables the proposed network to achieve global modeling of HSI comprehensively. From the perspective of feature alignment, we innovatively design the spatial fusion module (SpatialFM) and spectral fusion module (SpectralFM), aiming to preserve the comprehensively captured spatial correlations and spectral self-similarity. In this manner, the multiscale features can be better fused and the accuracy of reconstructed HSI can be significantly enhanced. Quantitative and qualitative experiments on the two largest SSR datasets (i.e., NTIRE2022 and NTIRE2020) demonstrate that our MSFN outperforms the state-of-the-art SSR methods. The code implementation will be uploaded at https://github.com/Matsuri247/MSFN-for-Spectral-Super-Resolution.

E2TNet: Efficient enhancement Transformer network for hyperspectral image classification

Recently, Convolutional Transformer-based models have become popular in hyperspectral image (HSI) classification tasks and gained competitive classification performance. However, some Convolutional Transformer-based models fail to effectively mine the global correlations of coarse-grained and fine-grained features, which is adverse to recognizing the refined scale variation information of land-cover. The combination of convolution operations and multihead self-attention mechanisms also increases the computational cost, leading to low classification efficiency. In addition, shallow spectral–spatial features are directly input into the encoder, which inevitably incurs redundant spectral information. Therefore, this paper proposes an efficient enhancement Transformer network (E2TNet) for HSI classification. Specifically, this paper first designs a spectral–spatial feature fusion module to extract spectral and spatial features from HSI cubes and fuse them. Second, considering that redundant spectral information has a negative impact on classification performance, this paper designs a spectral–spatial feature weighted module to improve the feature representation of critical spectral information. Finally, to explore the global correlations of coarse-grained and fine-grained features and improve classification efficiency, an efficient multigranularity information fusion module is embedded in the encoder of E2TNet. The experiment is conducted on four benchmark hyperspectral datasets, and the experimental results demonstrate that the proposed E2TNet is better than several Convolutional Transformer-based classification models in terms of classification accuracy and classification efficiency.

Unsupervised Hyperspectral and Multispectral Image Blind Fusion Based on Deep Tucker Decomposition Network With Spatial-Spectral Manifold Learning.

Hyperspectral image (HSI) and multispectral image (MSI) fusion aims to generate high spectral and spatial resolution hyperspectral image (HR-HSI) by fusing high-resolution multispectral image (HR-MSI) and low-resolution hyperspectral image (LR-HSI). However, existing fusion methods encounter challenges such as unknown degradation parameters, and incomplete exploitation of the correlation between high-dimensional structures and deep image features. To overcome these issues, in this article, an unsupervised blind fusion method for LR-HSI and HR-MSI based on Tucker decomposition and spatial-spectral manifold learning (DTDNML) is proposed. We design a novel deep Tucker decomposition network that maps LR-HSI and HR-MSI into a consistent feature space, achieving reconstruction through decoders with shared parameters. To better exploit and fuse spatial-spectral features in the data, we design a core tensor fusion network (CTFN) that incorporates a spatial-spectral attention mechanism for aligning and fusing features at different scales. Furthermore, to enhance the capacity to capture global information, a Laplacian-based spatial-spectral manifold constraint is introduced in shared-decoders. Sufficient experiments have validated that this method enhances the accuracy and efficiency of hyperspectral and multispectral fusion on different remote sensing datasets. The source code is available at https://github.com/Shawn-H-Wang/DTDNML.

Cnn-assisted multi-hop graph attention network for hyperspectral image classification

ABSTRACT Recently, the convolutional neural network (CNN) has gained widespread adoption in the hyperspectral image (HSI) classification owing to its remarkable feature extraction capability. However, the fixed acceptance domain of CNN restricts it to Euclidean image data only, making it difficult to capture complex information in hyperspectral data. To overcome this problem, much attention has been paid to the graph attention network (GAT), which can effectively model graph structure and capture complex dependencies between nodes. However, GAT usually acts on superpixel nodes, which may lead to the loss of pixel-level information. To better integrate the advantages of both, we propose a CNN-assisted multi-hop graph attention network (CMGAT) for HSI classification. Specifically, a parallel dual-branch architecture is first constructed to simultaneously capture spectral-spatial features from hyperspectral data at the superpixel and pixel levels using GAT and CNN, respectively. On this basis, the multi-hop and multi-scale mechanisms are further employed to construct a multi-hop GAT module and a multi-scale CNN module to capture diverse feature information. Secondly, an attention module is cascaded before the multi-scale CNN module to improve classification performance. Eventually, the output information from the two branches is weighted and fused to produce the classification result. We performed experiments on four benchmark HSI datasets, including Indian Pines (IP), University of Pavia (UP), Salinas Valley (SV) and WHU-Hi-LongKou (LK). The results demonstrate that the proposed method outperforms several deep learning methods, achieving overall accuracies of 95.67%, 99.04%, 99.55% and 99.51%, respectively, even with fewer training samples.

Interactive transformer and CNN network for fusion classification of hyperspectral and LiDAR data

ABSTRACT The Transformer has become pivotal for the integrated analysis of multi-source remote-sensing (RS) data in Earth observation, particularly in applications such as the fusion classification of hyperspectral images (HSI) and Light Detection and Ranging (LiDAR) data. However, Transformers are often employed as effective feature extractors by adopting similar processing blocks for different modalities from multi-source sensors, overlooking differences in imaging principles and data characteristics. Moreover, in the feature extraction process across different sensor data, there is a lack of necessary cross-modal information interaction, leading to insufficient utilization of complementary information between different sensors and resulting in suboptimal fusion outcomes. In this paper, we propose an interactive Transformer and CNN network for the fusion classification of HSI and LiDAR data. Specifically, a heterogeneous three-branch network architecture is designed for HSI and LiDAR data, where Transformers and CNNs encapsulate global contextual spatial and spectral information for HSI and capture geometric elevation patterns for LiDAR data, respectively. Elevation-Spatial Interaction (ESI) and Spectral-Spatial Interaction (SSI) modules are then introduced for multi-stage feature interaction. ESI enables the CNN-Transformer network to focus on essential local elevation details while simultaneously modelling global contextual spatial information. SSI facilitates the Transformer-Transformer network to cyclically intertwine spectral and spatial information for long-range spectral-spatial feature fusion. Finally, the interacted elevation, spatial, and spectral features undergo the Gated Fusion module to achieve hierarchical fusion adaptively, resulting in an elevation-spatial-spectral representation. Experiments conducted on three benchmark HSI-LiDAR datasets demonstrate the effectiveness of our proposed approach.

Local-global feature fusion network for hyperspectral image classification

ABSTRACT Hyperspectral images (HSIs) are rich in spatial and spectral information, making them crucial for accurate classification. While existing convolutional neural network (CNN) methods have shown promise in HSI classification, they primarily focus on local features and struggle with establishing long-range dependencies. To address these limitations, we propose a Local-Global Feature Fusion Network (LGFFN). LGFFN effectively learns joint local-global information from HSIs. Firstly, we employ a group-general convolution parallel module (GGCPM) to extract both local and global spectral features. Next, we utilize parallel branches: a CNN branch for capturing fine-grained spatial information and an improved transformer encoder (ITE) branch for capturing long-distance spatial-spectral features and exploiting semantic information. Finally, we elegantly integrate the diverse features obtained from these branches to obtain classification results. We validate our method on four datasets and compare it with six state-of-the-art hyperspectral classification methods. Our experimental results demonstrate that LGFFN achieves high classification accuracy, outperforming existing methods.

A Representation-Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection

Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalanced number between the target and the background spatially and the high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation-learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and spatial–spectral features to improve its representation ability. Firstly, a Graph Convolutional Network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene’s underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing the detection and background suppression capabilities. The performance of the proposed approach is evaluated using the average scores of AUCD,F, AUCF,τ, AUCBS, and AUCSNPR. The corresponding values are 0.99660, 0.00078, 0.99587, and 333.629, respectively. These results demonstrate the accuracy of the model in different evaluation metrics, with AUCD,F achieving the highest score, indicating strong detection performance across varying thresholds. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture.

PGNN-Net: Parallel Graph Neural Networks for Hyperspectral Image Classification Using Multiple Spatial-Spectral Features

Hyperspectral image (HSI) shows great potential for application in remote sensing due to its rich spectral information and fine spatial resolution. However, the high dimensionality, nonlinearity, and complex relationship between spectral and spatial features of HSI pose challenges to its accurate classification. Traditional convolutional neural network (CNN)-based methods suffer from detail loss in feature extraction; Transformer-based methods rely too much on the quantity and quality of HSI; and graph neural network (GNN)-based methods provide a new impetus for HSI classification by virtue of their excellent ability to handle irregular data. To address these challenges and take advantage of GNN, we propose a network of parallel GNNs called PGNN-Net. The network first extracts the key spatial-spectral features of HSI using principal component analysis, followed by preprocessing to obtain two primary features and a normalized adjacency matrix. Then, a parallel architecture is constructed using improved GCN and ChebNet to extract local and global spatial-spectral features, respectively. Finally, the discriminative features obtained through the fusion strategy are input into the classifier to obtain the classification results. In addition, to alleviate the over-fitting problem, the label smoothing technique is embedded in the cross-entropy loss function. The experimental results show that the average overall accuracy obtained by our method on Indian Pines, Kennedy Space Center, Pavia University Scene, and Botswana reaches 97.35%, 99.40%, 99.64%, and 98.46%, respectively, which are better compared to some state-of-the-art methods.

Class incremental learning with analytic learning for hyperspectral image classification

Hyperspectral image classification (HSIC) is crucial for applications in agriculture and environmental monitoring. As ground objects evolve and remote sensing technology progresses, there is a growing need for HSIC models that can adapt to new data classes without requiring to be retrained from scratch. Throughout the continual learning procedure, the model is expected to not only effectively extract spatial–spectral features from the hyperspectral image but also alleviate the issue of catastrophic forgetting, i.e., the model forgets the learned classes’ knowledge when accessing novel classes during the training process. In this paper, for the HSIC task, we propose a class incremental learning method (HSI-CIL) that is based on analytic learning, a technique that converts network training into linear problems. Specifically, The HSI-CIL model consists of a lightweight feature extractor, a Feature Processing Module (FPM) and an Analytic Linear Classifier (ALC). This model does not need data storage for old and new classes and has only one epoch in the incremental learning stage, so it has lower consumption of resources and training time than several attempts have been proposed for addressing catastrophic forgetting. We perform abundant experiments with the proposed HSI-CIL on three publicly available hyperspectral datasets including Indian Pines, Pavia University, and Salinas. The experiments demonstrate that our HSI-CIL exceeds the state-of-the-art class incremental learning (CIL) techniques applied in HSIC with a certain gap.

AMHFN: Aggregation Multi-Hierarchical Feature Network for Hyperspectral Image Classification

Deep learning methods like convolution neural networks (CNNs) and transformers are successfully applied in hyperspectral image (HSI) classification due to their ability to extract local contextual features and explore global dependencies, respectively. However, CNNs struggle in modeling long-term dependencies, and transformers may miss subtle spatial-spectral features. To address these challenges, this paper proposes an innovative hybrid HSI classification method aggregating hierarchical spatial-spectral features from a CNN and long pixel dependencies from a transformer. The proposed aggregation multi-hierarchical feature network (AMHFN) is designed to capture various hierarchical features and long dependencies from HSI, improving classification accuracy and efficiency. The proposed AMHFN consists of three key modules: (a) a Local-Pixel Embedding module (LPEM) for capturing prominent spatial-spectral features; (b) a Multi-Scale Convolutional Extraction (MSCE) module to capture multi-scale local spatial-spectral features and aggregate hierarchical local features; (c) a Multi-Scale Global Extraction (MSGE) module to explore multi-scale global dependencies and integrate multi-scale hierarchical global dependencies. Rigorous experiments on three public hyperspectral image (HSI) datasets demonstrated the superior performance of the proposed AMHFN method.

ANN-Based Filtering of Drone LiDAR in Coastal Salt Marshes Using Spatial–Spectral Features

ANN-Based Filtering of Drone LiDAR in Coastal Salt Marshes Using Spatial–Spectral Features

STSNet: A cross-spatial resolution multi-modal remote sensing deep fusion network for high resolution land-cover segmentation

Recently, deep learning models have found extensive application in high-resolution land-cover segmentation research. However, the most current research still suffers from issues such as insufficient utilization of multi-modal information, which limits further improvement in high-resolution land-cover segmentation accuracy. Moreover, differences in the size and spatial resolution of multi-modal datasets collectively pose challenges to multi-modal land-cover segmentation. Therefore, we propose a high-resolution land-cover segmentation network (STSNet) with cross-spatial resolution spatio-temporal-spectral deep fusion. This network effectively utilizes spatio-temporal-spectral features to achieve information complementary among multi-modal data. Specifically, STSNet consists of four components: (1) A high resolution and multi-scale spatial-spectral encoder to jointly extract subtle spatial-spectral features in hyperspectral and high spatial resolution images. (2) A long-term spatio-temporal encoder formulated by spectral convolution and spatio-temporal transformer block to simultaneously delineates the spatial, temporal and spectral information in dense time series Sentinel-2 imagery. (3) A cross-resolution fusion module to alleviate the spatial resolution differences between multi-modal data and effectively leverages complementary spatio-temporal-spectral information. (4) A multi-scale decoder integrates multi-scale information from multi-modal data. We utilized airborne hyperspectral remote sensing imagery from the Shenyang region of China in 2020, with a spatial resolution of 1authors declare that they have no known competm, a spectral number of 249, and a spectral resolution ≤ 5 nm, and its Sentinel dense time-series images acquired in the same period with a spatial resolution of 10 m, a spectral number of 10, and a time-series number of 31. These datasets were combined to generate a multi-modal dataset called WHU-H2SR-MT, which is the first open accessed large-scale high spatio-temporal-spectral satellite remote sensing dataset (i.e., with >2500 image pairs sized 300 m × 300 m for each). Additionally, we employed two open-source datasets to validate the effectiveness of the proposed modules. Extensive experiments show that our multi-scale spatial-spectral encoder, spatio-temporal encoder, and cross-resolution fusion module outperform existing state-of-the-art (SOTA) algorithms in terms of overall performance on high-resolution land-cover segmentation. The new multi-modal dataset will be made available at http://irsip.whu.edu.cn/resources/resources_en_v2.php, along with the corresponding code for accessing and utilizing the dataset at https://github.com/RS-Mage/STSNet.