YMYong Mei

Yong Mei

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yong Mei has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SFE-FM: A Dual-Branch Network with Spectral Feature Enhancement and Feature Mixing for Hyperspectral Image Classification

    by Xiangsuo Fan, Guilan Huang, Yong Mei, Peng Li

    Hyperspectral image (HSI) classification remains a challenging task due to its high-dimensional spectral characteristics and the complex spatial heterogeneity of remote sensing scenes. Although significant progress has been made with convolutional neural networks (CNNs) and Transformer methods, existing approaches often fail to adequately model fine-grained variations in spectral curves, whilst struggling to strike a good balance between preserving local texture and modelling global context. To this end, this paper proposes a spatial–spectral dual-branch network (SFE-FM) for HSI classification, which combines spectral feature enhancement with a lightweight feature fusion mechanism to improve feature representational capacity. Specifically, a Spectral Feature Enhancement (SFE) module is designed to explicitly model spectral trends through first- and second-order differential operations, thereby enhancing potential discriminative information; at the same time, a lightweight Feature Mixing (FM) module is introduced into the network to model global dependencies across channels. In the dual-branch architecture, the spatial branch and the spectral branch extract spatial texture features and spectral semantic features respectively, and these features are adaptively reweighted using a cross-branch-guided fusion strategy (CSSF) to facilitate the effective integration of the two types of information. In addition, a multi-scale attention optimisation module (MSAO) has been introduced to enhance the response in key areas and improve the robustness of feature representations. Experiments conducted on the four benchmark datasets—WHU-Hi-HanChuan, Qingyun, Salinas and Pavia University, the proposed method achieved overall classification accuracies of 99.62%, 98.70%, 99.97% and 99.81%, respectively. Whilst maintaining a relatively low number of parameters (0.631M), it delivered competitive performance, demonstrating a good balance between classification accuracy and computational efficiency.

  • Open Access

    PSTNet: A Hyperspectral Image Classification Method Based on Adaptive Spectral–Spatial Tokens and Parallel Attention

    by Shaokang Yu, Yong Mei, Xiangsuo Fan, Song Guo, Wujun Xu, Jinlong Fan

    Hyperspectral image classification holds significant applications across multiple domains due to its rich spectral and spatial information. However, it faces challenges such as spectral variation within the same object, spectral variation across different objects, and noise interference. Existing methods like convolutional neural networks perform well in local feature extraction but inadequately model long-range dependencies. While Transformers can capture global relationships, they struggle to effectively coordinate spectral and spatial information modeling. To address these limitations, this paper proposes a dual-branch collaborative Transformer network (PST-Net). This architecture integrates an adaptive spectral–spatial token (ASST) module, a Parallel Attention-Augmented lightweight CNN branch (PA-SSCNN), and a collaborative fusion layer. The ASST constructs joint representation tokens through local spectral smoothing and learnable spatial embedding. PA-SSCNN employs 3D-2D cascaded convolutions and channel–spatial attention mechanisms to enhance local texture and spatial feature extraction; CHIB enables deep interaction and synergistic fusion of dual-branch features across different levels and scales. Experimental results demonstrate that with only 2% labeled samples, PST-Net achieves overall classification accuracies of 96.31%, 96.59%, 95.27%, and 89.06% on the Salinas and Whuhh, and the two complex urban scene datasets Qingyun and Houston. Especially in fine-grained categories and complex scenes, it exhibits strong robustness. The ablation experiment further validated the effectiveness and complementarity of each module. This study provides an efficient collaborative modeling framework for hyperspectral image classification that balances global dependencies and local details.


  • Open Access

    GASE-Net: Spatial Channel Enhancement and Adaptive Fusion of Graph Attention for Hyperspectral Image Classification

    by Xiangsuo Fan, Yong Mei, Jinlong Fan, Xuyang Li

    In recent years, convolutional neural networks (CNNs) and graph neural networks (GNNs) have been widely applied to hyperspectral remote sensing image classification. However, CNNs rely on fixed-size convolutional kernels for feature extraction, resulting in limited receptive fields that struggle to capture relationships between distant pixels in hyperspectral images. While GNN-based hyperspectral classification methods effectively mine features in non-Euclidean hyperspectral data, they face significant challenges in constructing graph structures. For instance, traditional graph convolutional networks typically rely on local neighborhood connections, making it difficult to directly model spatial relationships between pixels at extreme distances. This limits their ability to effectively extract long-range interaction information within images. To address these challenges, this paper proposes GASE-Net, a network for hyperspectral image classification. Adopting a parallel architecture, it integrates a CNN with channel-spatial attention and a gated graph attention network, while incorporating noise reduction and feature enhancement modules at the front end to boost feature representation capabilities. The proposed network fuses features from two branches through an adaptive weighting mechanism. On one hand, it models and captures spectral-spatial features from non-Euclidean hyperspectral images based on graph structures, effectively characterizing relationships between pixels at ultra-long distances. On the other hand, it employs a pixel-level convolutional neural network with a fused channel-spatial attention mechanism to extract fine-grained spatial features, thereby overcoming the inherent limitations of convolutional neural networks in modeling long-range relationships. Experiments on the Salina, WHU-Hi-HanChuan, WHU-Hi-HongHu, Pingan, Qingyun, and Indian Pines dataset, the proposed method achieves overall classification accuracies of 99.33%, 98.24%, 98.57%, 98.41%, 97.83% and 94.02%, respectively. Compared with other models, GASE-Net demonstrates strong generalization capabilities and excellent classification performance in hyperspectral remote sensing image classification.


  • Open Access

    DuFANet: A Multisource Remote Sensing Image Classification Method Integrating Frequency-Domain Attention and Cross-Modal Transformers

    by Yong Mei, Xiangsuo Fan, Jinlong Fan

    Joint classification of hyperspectral imagery with LiDAR and SAR multimodal remote sensing data holds significant value for enhancing feature recognition accuracy. However, it still faces challenges such as severe spectral interference, modal imbalance, and insufficient feature fusion. To address these challenges, this paper proposes a multi-source fusion network-DuFANet. This approach introduces a frequency-domain attention module (FreqAttnBlock) in the hyperspectral branch to explicitly decompose and enhance spectral-spatial features. In the LiDAR/SAR branch, a depthwise convolutional self-attention module (DWConvSelfBlock) is designed to efficiently model modal local geometric features and global contextual information. A parallel Transformer encoder is employed after both hyperspectral and LiDAR/SAR branches to capture long-range dependencies and global semantics. The fusion stage introduces a dual-branch cross-modal fusion attention module (DuFuseAttention), achieving stable complementarity through dual-layer mechanisms at both the channel and spatial dimensions. Experiments on five datasets-Berlin, Muufl, Houston2013, Augsburg, and Trento, DuFANet achieves overall classification accuracies of 79.29%, 92.31%, 99.44%, 97.59%, and 99.75% respectively, significantly outperforming existing methods. Furthermore, the model demonstrates exceptional performance in complex urban scenes and under few-shot conditions, achieving a favorable balance between accuracy and computational cost. The source codes of DuFANet will be publicly available at https://github.com/zwyxmy/DuFANet.git.


  • Open Access

    CSTC: Visual Transformer Network with Multimodal Dual Fusion for Hyperspectral and LiDAR Image Classification

    by Yong Mei, Jinlong Fan, Xiangsuo Fan, Qi Li

    Convolutional neural networks have made significant progress in multimodal remote sensing image classification, but traditional convolutional neural networks are limited by fixed-size convolutional kernels, which are unable to effectively model and adequately extract contextual information; hyperspectral imagery and LiDAR data have comparatively large information differences, which do not allow for effective information interaction and fusion. Based on this, this paper proposes a multimodal dual fusion network (CSTC) based on the Vision Transformer for the collaborative classification of HSI and LiDAR data. The model is designed through a two-branch architecture: the HSI branch extracts spectral–spatial features by dimensionality reduction using principal component analysis and inputs them into the cross-connectivity feature fusion module; the LiDAR branch mines spatial elevation features through the stacked MobileNetV2 module. The features of the two branches are encoded by a Transformer, and the modal interaction fusion is realized by the cross-attention module for the first time. Then, the features are spliced and input into the secondary Transformer for deep cross-modal fusion, and finally, the classification is completed by the multilayer perceptron. Experiments show that the CSTC model achieves overall classification accuracies of 92.32%, 99.81%, 97.90%, and 99.37% on the publicly available MUUFL dataset, Trento dataset, Augsburg dataset, and Houston2013 dataset, respectively, which is superior to the latest HSI–LiDAR separate classification algorithms. The ablation experiments and model performance evaluation experiments further show that the proposed CSTC model achieves excellent results in terms of robustness, adaptability, and parameter scale.