Wen Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wen Lu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Le Sun
School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China
4 shared publications - Xiaolei Gu
Department of Public Security of Qinghai Province, Xining, Qinghai, China
4 shared publications - Qiaolin Ye
School of Information Science and Technology, Nanjing Forest University, Nanjing 210037, China
3 shared publications - Yulin Cao
Qinghai Normal University
3 shared publications - Zhonglin Ye
School of Computer, Qinghai Normal University, Xining, Qinghai, China
3 shared publications - Xuanrong Huo
School of Computer, Qinghai Normal University, Xining, PR China
2 shared publications
Latest Publications
- Open Access
- 2 October 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (19) , 3381
From Prior to Frequency: A Progressive Structure Recovery Network for Remote Sensing Road Segmentation
Roads in remote sensing imagery often contain narrow branches, complex boundaries, and long-range connections. Background interference and repeated downsampling make these structures difficult to preserve. To address these challenges, we propose a Progressive Structure Recovery Network (PSRNet) for remote sensing road segmentation. The network integrates structural-prior guidance, frequency-domain enhancement, and multiscale decoding. A line-structure prior is generated from the input image and encoded alongside hierarchical image features. Local Detail Alignment integrates prior cues with shallow features to enhance local structural details. Structure–Semantic Alignment combines deep semantic features with structural cues to refine unreliable prior responses. At the bottleneck, a Frequency Detail-Aware Enhancement module adaptively modulates the amplitude spectrum of the aligned features while preserving phase information. The reconstructed features are combined with spatial representations through residual fusion. A deep-to-shallow progressive decoder then restores spatial details and generates multiscale side predictions, which are fused to produce the final segmentation map. Experiments on the Massachusetts Roads, DeepGlobe, and CHN6-CUG datasets demonstrate the effectiveness of PSRNet for road segmentation. Ablation studies further support the complementary contributions of structural-prior guidance, frequency-domain enhancement, and progressive decoding.
- 2 October 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (19) , 3381
Open AccessFrom Prior to Frequency: A Progressive Structure Recovery Network for Remote Sensing Road Segmentation
Roads in remote sensing imagery often contain narrow branches, complex boundaries, and long-range connections. Background interference and repeated downsampling make these structures difficult to preserve. To address these challenges, we propose a Progressive Structure Recovery Network (PSRNet) for remote sensing road segmentation. The network integrates structural-prior guidance, frequency-domain enhancement, and multiscale decoding. A line-structure prior is generated from the input image and encoded alongside hierarchical image features. Local Detail Alignment integrates prior cues with shallow features to enhance local structural details. Structure–Semantic Alignment combines deep semantic features with structural cues to refine unreliable prior responses. At the bottleneck, a Frequency Detail-Aware Enhancement module adaptively modulates the amplitude spectrum of the aligned features while preserving phase information. The reconstructed features are combined with spatial representations through residual fusion. A deep-to-shallow progressive decoder then restores spatial details and generates multiscale side predictions, which are fused to produce the final segmentation map. Experiments on the Massachusetts Roads, DeepGlobe, and CHN6-CUG datasets demonstrate the effectiveness of PSRNet for road segmentation. Ablation studies further support the complementary contributions of structural-prior guidance, frequency-domain enhancement, and progressive decoding.
- Open Access
- 20 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3234
FCD-Mamba: A Frequency-Enhanced and Center-Pixel-Guided Dual-Branch Mamba Network for Hyperspectral Image Classification
Hyperspectral image classification is an important task in remote sensing image interpretation. However, existing Mamba-based methods remain limited in exploiting shallow frequency information, preserving neighborhood continuity during spatial serialization, and protecting center-pixel semantics. To address these limitations, we propose a frequency-enhanced and center-pixel-guided dual-branch Mamba network (FCD-Mamba). First, the Frequency-Enhanced Multiscale Convolution Module (FEMSCM) applies serial Fourier filtering to enhance multiscale spatial features and calibrates spectral features using low-, middle-, and high-frequency DCT energy descriptors derived from the original spectrum of the center pixel. Second, the Spatial Center-Adaptive Mamba (SCA-Mamba) employs two orthogonal Hilbert curves and their reverse traversals to preserve spatial neighborhood continuity, while adaptively aggregating multi-path features using center and global representations. The Spectral Center-Preserving Mamba (SCP-Mamba) constructs center-preserved and global spectral sequences and models their complementary spectral dependencies through bidirectional scanning. Finally, the Center-Pixel-Guided Residual Fusion Module (CGRFM) exploits center-to-global discrepancies to calibrate dual-branch features and introduces auxiliary supervision to maintain the discriminability of each branch. Experiments on multiple public hyperspectral datasets demonstrate that FCD-Mamba achieves stable and competitive classification performance, validating the effectiveness of its constituent modules.
- 20 September 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (18) , 3234
Open AccessFCD-Mamba: A Frequency-Enhanced and Center-Pixel-Guided Dual-Branch Mamba Network for Hyperspectral Image Classification
Hyperspectral image classification is an important task in remote sensing image interpretation. However, existing Mamba-based methods remain limited in exploiting shallow frequency information, preserving neighborhood continuity during spatial serialization, and protecting center-pixel semantics. To address these limitations, we propose a frequency-enhanced and center-pixel-guided dual-branch Mamba network (FCD-Mamba). First, the Frequency-Enhanced Multiscale Convolution Module (FEMSCM) applies serial Fourier filtering to enhance multiscale spatial features and calibrates spectral features using low-, middle-, and high-frequency DCT energy descriptors derived from the original spectrum of the center pixel. Second, the Spatial Center-Adaptive Mamba (SCA-Mamba) employs two orthogonal Hilbert curves and their reverse traversals to preserve spatial neighborhood continuity, while adaptively aggregating multi-path features using center and global representations. The Spectral Center-Preserving Mamba (SCP-Mamba) constructs center-preserved and global spectral sequences and models their complementary spectral dependencies through bidirectional scanning. Finally, the Center-Pixel-Guided Residual Fusion Module (CGRFM) exploits center-to-global discrepancies to calibrate dual-branch features and introduces auxiliary supervision to maintain the discriminability of each branch. Experiments on multiple public hyperspectral datasets demonstrate that FCD-Mamba achieves stable and competitive classification performance, validating the effectiveness of its constituent modules.
- Open Access
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 9-14
The Optimal Allocation Strategy of Computing Power Network Resources
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 9-14
Open AccessThe Optimal Allocation Strategy of Computing Power Network Resources
- Open Access
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 69-75
A Review of Anomaly Detection Methods for Smart Water Distribution Networks
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 69-75
Open AccessA Review of Anomaly Detection Methods for Smart Water Distribution Networks
- Open Access
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 24-30
Large Models in Smart Water Systems
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 24-30
Open AccessLarge Models in Smart Water Systems
- Open Access
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 158-163
Overview of Optimal Resource Allocation in Computing Networks-Optimal Resource Allocation in Computing Networks
In recent years, the rapid advancement of computing power networks and computing-network integration has made the coordinated scheduling of network and computing resources a critical component of next-generation information infrastructure. Resource scheduling in cloud-edge-end collaborative environments exhibits high heterogeneity, strong coupling, and dynamic complexity. This challenges traditional optimization methods, such as mathematical programming and heuristic algorithms, by introducing modeling difficulties and real-time limitations in large-scale, complex scenarios. However, the introduction of reinforcement learning, graph neural networks, and large models into computing network resource scheduling has successfully advanced scheduling mechanisms toward intelligence, adaptability, and cross-scenario generalization. This paper systematically reviews optimal allocation methods for computing network resources, categorizes and summarizes research progress in traditional optimization methods, reinforcement learning approaches, graph neural network methods, and large-model techniques, and compares the capability boundaries of these methods. Finally, it discusses current research challenges and future development trends.
- 3 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 158-163
Open AccessOverview of Optimal Resource Allocation in Computing Networks-Optimal Resource Allocation in Computing Networks
In recent years, the rapid advancement of computing power networks and computing-network integration has made the coordinated scheduling of network and computing resources a critical component of next-generation information infrastructure. Resource scheduling in cloud-edge-end collaborative environments exhibits high heterogeneity, strong coupling, and dynamic complexity. This challenges traditional optimization methods, such as mathematical programming and heuristic algorithms, by introducing modeling difficulties and real-time limitations in large-scale, complex scenarios. However, the introduction of reinforcement learning, graph neural networks, and large models into computing network resource scheduling has successfully advanced scheduling mechanisms toward intelligence, adaptability, and cross-scenario generalization. This paper systematically reviews optimal allocation methods for computing network resources, categorizes and summarizes research progress in traditional optimization methods, reinforcement learning approaches, graph neural network methods, and large-model techniques, and compares the capability boundaries of these methods. Finally, it discusses current research challenges and future development trends.
- Open Access
- 20 February 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (4) , 649
EIMGDNet: An Edge-Induced and Multi-Dimensional Grouped Difference Network for Remote Sensing Image Change Detection
Change detection in remote sensing imagery is crucial for monitoring temporal variations in surface characteristics; nevertheless, it presents significant challenges owing to indistinct boundaries, limited semantic differentiation, and inadequate incorporation of multi-scale contextual information. To solve these problems, we propose EIMDGNet (Edge-Induced and Multi-Dimensional Grouped Difference Network), a novel architecture that enhances boundary representation and cross-scale feature interaction for accurate and robust change detection. EIMDGNet adopts a dual-branch ResNet18 backbone to extract multi-scale features from bi-temporal images, capturing both fine spatial detail and high-level semantic context. To improve boundary awareness and reduce pseudo-change interference, we introduce the Edge-Induced Differential Multi-Dimensional Group Enhancement Module (EID-MDGEM). This module enriches fine-grained spatial features through grouped pooling across spatial and channel dimensions, enabling precise localization of change contours. Within EID-MDGEM, the Edge Feature Enhancement Module (EFEM) integrates a parameter-free attention mechanism to generate edge-saliency maps, highlighting true change regions while suppressing background noise and irrelevant variations. To further enhance semantic consistency across feature scales, we design the Multi-Scale Hierarchical Progressive Fusion Module (MSHPM). This component employs a bottom-up progressive strategy to hierarchically integrate low-level spatial details with high-level semantic abstractions, thus increasing the continuity and completeness of detected change regions. By tightly coupling edge-aware enhancement with multi-scale hierarchical fusion, EIMDGNet effectively addresses major obstacles in change detection, including boundary ambiguity, inconsistent scale information, and feature misalignment. We evaluated EIMDGNet on five remote sensing change detection datasets: LEVIR-CD, DSIFN-CD, S2Looking, CLCD-CD and GVLM-CD. Our method consistently outperformed state-of-the-art approaches, achieving 91.49% F1 and 82.93% IoU on LEVIR-CD, 77.32% F1 and 69.39% IoU on DSIFN-CD, the highest 49.19% IoU and 99.20% OA on S2Looking, 81.65% F1 and 72.91% IoU on CLCD-CD, and 85.49% F1 and 76.08% IoU on GVLM-CD. These results demonstrate the superior accuracy and robustness of EIMDGNet across diverse change detection scenarios.
- 20 February 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (4) , 649
Open AccessEIMGDNet: An Edge-Induced and Multi-Dimensional Grouped Difference Network for Remote Sensing Image Change Detection
Change detection in remote sensing imagery is crucial for monitoring temporal variations in surface characteristics; nevertheless, it presents significant challenges owing to indistinct boundaries, limited semantic differentiation, and inadequate incorporation of multi-scale contextual information. To solve these problems, we propose EIMDGNet (Edge-Induced and Multi-Dimensional Grouped Difference Network), a novel architecture that enhances boundary representation and cross-scale feature interaction for accurate and robust change detection. EIMDGNet adopts a dual-branch ResNet18 backbone to extract multi-scale features from bi-temporal images, capturing both fine spatial detail and high-level semantic context. To improve boundary awareness and reduce pseudo-change interference, we introduce the Edge-Induced Differential Multi-Dimensional Group Enhancement Module (EID-MDGEM). This module enriches fine-grained spatial features through grouped pooling across spatial and channel dimensions, enabling precise localization of change contours. Within EID-MDGEM, the Edge Feature Enhancement Module (EFEM) integrates a parameter-free attention mechanism to generate edge-saliency maps, highlighting true change regions while suppressing background noise and irrelevant variations. To further enhance semantic consistency across feature scales, we design the Multi-Scale Hierarchical Progressive Fusion Module (MSHPM). This component employs a bottom-up progressive strategy to hierarchically integrate low-level spatial details with high-level semantic abstractions, thus increasing the continuity and completeness of detected change regions. By tightly coupling edge-aware enhancement with multi-scale hierarchical fusion, EIMDGNet effectively addresses major obstacles in change detection, including boundary ambiguity, inconsistent scale information, and feature misalignment. We evaluated EIMDGNet on five remote sensing change detection datasets: LEVIR-CD, DSIFN-CD, S2Looking, CLCD-CD and GVLM-CD. Our method consistently outperformed state-of-the-art approaches, achieving 91.49% F1 and 82.93% IoU on LEVIR-CD, 77.32% F1 and 69.39% IoU on DSIFN-CD, the highest 49.19% IoU and 99.20% OA on S2Looking, 81.65% F1 and 72.91% IoU on CLCD-CD, and 85.49% F1 and 76.08% IoU on GVLM-CD. These results demonstrate the superior accuracy and robustness of EIMDGNet across diverse change detection scenarios.
- Open Access
- 23 December 2023
- Published by MDPI AG in Remote Sensing
- Vol. 16 (1) , 67
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.
- 23 December 2023
- Published by MDPI AG in Remote Sensing
- Vol. 16 (1) , 67
Open AccessSpectral–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.