Yanhui Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yanhui Guo has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Yu Bai
Department of Electrical and Computer Engineering, California State University Fullerton, Fullerton, USA
6 shared publications Danqing Liu
4 shared publications- Anming Dong
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China
2 shared publications Bingyu Yan
Shandong Provincial Key Laboratory of Infectious Disease Control and Prevention, Shandong Center for Disease Control and Prevention, Jinan, Shandong, China
2 shared publicationsGuanliang Wan
School of Artificial Intelligence, Shandong Womens University, Jinan, China
2 shared publications- Han Cao
School of Computer Science, Shaanxi Normal University, Xi’an, China
2 shared publications
Latest Publications
- Open Access
- 23 June 2026
- Published by Elsevier in SSRN Electronic Journal
A Dual-Encoder Framework with Global-to-Local Modulation for Multi-Class Unsupervised Anomaly Detection
Reconstruction-based methods leveraging Vision Transformers (ViT) have demonstrated significant potential in unsupervised industrial anomaly detection. However, existing single-stream architectures struggle with an inherent trade-off when processing multi-scale features: while high-resolution features enhance pixel-level localization, they often introduce local noise that degrades image-level detection performance. To resolve this conflict between global semantic stability and local detail sensitivity, we propose a dual-encoder framework named GLM-AD (Global-to-Local Modulation for Anomaly Detection). In which, the global encoder captures stable structural semantics, while the local encoder focuses on fine-grained defect-sensitive patterns. On top of this architecture, we introduce a Global-to-Local Feature Modulation (GLFM) module, which performs channel-wise modulation to implicitly constrain local feature reconstruction using global semantic cues. Furthermore, to cope with the significant morphological heterogeneity of industrial anomalies, we propose a Multi-Scale Ensemble Scoring (MSE-Scoring) strategy. As a model-agnostic and label-free post-processing scheme, MSE-Scoring integrates anomaly responses across multiple observation profiles, effectively alleviating the signal-to-noise imbalance inherent in high-resolution features. Extensive experiments conducted on three public industrial benchmarks(MVTec-AD, VisA, and Real-IAD) demonstrate that GLM-AD consistently achieves state-of-the-art performance in terms of detection robustness and localization accuracy, validating its effectiveness and practical applicability in real-world industrial inspection scenarios.
- 23 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Dual-Encoder Framework with Global-to-Local Modulation for Multi-Class Unsupervised Anomaly Detection
Reconstruction-based methods leveraging Vision Transformers (ViT) have demonstrated significant potential in unsupervised industrial anomaly detection. However, existing single-stream architectures struggle with an inherent trade-off when processing multi-scale features: while high-resolution features enhance pixel-level localization, they often introduce local noise that degrades image-level detection performance. To resolve this conflict between global semantic stability and local detail sensitivity, we propose a dual-encoder framework named GLM-AD (Global-to-Local Modulation for Anomaly Detection). In which, the global encoder captures stable structural semantics, while the local encoder focuses on fine-grained defect-sensitive patterns. On top of this architecture, we introduce a Global-to-Local Feature Modulation (GLFM) module, which performs channel-wise modulation to implicitly constrain local feature reconstruction using global semantic cues. Furthermore, to cope with the significant morphological heterogeneity of industrial anomalies, we propose a Multi-Scale Ensemble Scoring (MSE-Scoring) strategy. As a model-agnostic and label-free post-processing scheme, MSE-Scoring integrates anomaly responses across multiple observation profiles, effectively alleviating the signal-to-noise imbalance inherent in high-resolution features. Extensive experiments conducted on three public industrial benchmarks(MVTec-AD, VisA, and Real-IAD) demonstrate that GLM-AD consistently achieves state-of-the-art performance in terms of detection robustness and localization accuracy, validating its effectiveness and practical applicability in real-world industrial inspection scenarios.
- Open Access
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 15392-15410
SSFNet: Spatial–Spectral Frequency-Aware Network for Hyperspectral Image Classification
Spatial–spectral modeling methods have achieved remarkable progress in hyperspectral image (HSI) classification. However, most existing approaches primarily emphasize spatial–spectral feature fusion or multi-scale representation learning, while the intrinsic frequency-discriminative characteristics of spatial and spectral signals remain underexplored for coordinated local–global modeling. To address these issues, we propose a novel Spatial–Spectral Frequency-Aware Network (SSFNet) for hyperspectral image classification. SSFNet adopts a dual-branch architecture, consisting of a Frequency-Aware Spatial Modeling (FASM) branch and a Frequency-Based Spectral Modeling (FBSM) branch. The spatial branch (FASM) enhances boundary sensitivity and global contextual consistency through explicit high–low frequency modulation, enabling improved spatial representation learning. The FBSM branch performs spectral frequency decomposition, where the low-frequency component captures smooth, large-scale spectral trends, and the high-frequency component models fine-grained variations and discriminative fluctuations. A gated fusion mechanism is further designed to adaptively integrate complementary frequency features across different scales. Extensive experiments on four benchmark datasets demonstrate that SSFNet consistently outperforms eight state-of-the-art methods in terms of classification accuracy and generalization capability. These results verify the effectiveness of explicit frequency-aware spatial–spectral modeling for hyperspectral image classification.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 15392-15410
Open AccessSSFNet: Spatial–Spectral Frequency-Aware Network for Hyperspectral Image Classification
Spatial–spectral modeling methods have achieved remarkable progress in hyperspectral image (HSI) classification. However, most existing approaches primarily emphasize spatial–spectral feature fusion or multi-scale representation learning, while the intrinsic frequency-discriminative characteristics of spatial and spectral signals remain underexplored for coordinated local–global modeling. To address these issues, we propose a novel Spatial–Spectral Frequency-Aware Network (SSFNet) for hyperspectral image classification. SSFNet adopts a dual-branch architecture, consisting of a Frequency-Aware Spatial Modeling (FASM) branch and a Frequency-Based Spectral Modeling (FBSM) branch. The spatial branch (FASM) enhances boundary sensitivity and global contextual consistency through explicit high–low frequency modulation, enabling improved spatial representation learning. The FBSM branch performs spectral frequency decomposition, where the low-frequency component captures smooth, large-scale spectral trends, and the high-frequency component models fine-grained variations and discriminative fluctuations. A gated fusion mechanism is further designed to adaptively integrate complementary frequency features across different scales. Extensive experiments on four benchmark datasets demonstrate that SSFNet consistently outperforms eight state-of-the-art methods in terms of classification accuracy and generalization capability. These results verify the effectiveness of explicit frequency-aware spatial–spectral modeling for hyperspectral image classification.
- Open Access
- 13 April 2026
- Published by Elsevier in SSRN Electronic Journal
HyperMODE: A Continuous-Depth Spectral–Spatial Modeling Framework with Mamba and Neural Ordinary Differential Equations for Hyperspectral Image Classification
Hyperspectral image (HSI) classification requires jointly capturing fine-grained spectral–spatial patterns and long-range contextual dependencies. However, existing convolutional, Transformer-based, and recent state-space architectures mainly rely on fixed discrete layer-wise transformations, which may lead to fragmented intermediate feature updates and insufficient coordination between multi-scale local representation learning and global spatial propagation. To address this issue, we propose HyperMODE, a unified continuous–discrete spectral–spatial modeling framework for HSI classification. Specifically, HyperMODE first constructs multi-scale spectral–spatial representations from compact input patches, and then couples Neural ODE-based continuous-depth feature evolution with scale-diverse Mamba-based spatial propagation through an interval-coupled pipeline. In this framework, Neural ODE enables smoother and more consistent feature transformation in the reduced representation space, while the multi-branch Mamba architecture performs efficient long-range spatial propagation and cross-scale context interaction with linear complexity. By unifying continuous feature evolution and efficient spatial propagation, HyperMODE establishes a coherent hybrid paradigm for spectral–spatial representation learning. Extensive experiments on four public HSI benchmarks, including Pavia University, WHU-Hi-HanChuan, WHU-Hi-LongKou, and Houston 2013, demonstrate stable and competitive classification performance, validating the effectiveness of the proposed framework. The source code will be made available at https://github.com/JaylenTang/HyperMODE.
- 13 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessHyperMODE: A Continuous-Depth Spectral–Spatial Modeling Framework with Mamba and Neural Ordinary Differential Equations for Hyperspectral Image Classification
Hyperspectral image (HSI) classification requires jointly capturing fine-grained spectral–spatial patterns and long-range contextual dependencies. However, existing convolutional, Transformer-based, and recent state-space architectures mainly rely on fixed discrete layer-wise transformations, which may lead to fragmented intermediate feature updates and insufficient coordination between multi-scale local representation learning and global spatial propagation. To address this issue, we propose HyperMODE, a unified continuous–discrete spectral–spatial modeling framework for HSI classification. Specifically, HyperMODE first constructs multi-scale spectral–spatial representations from compact input patches, and then couples Neural ODE-based continuous-depth feature evolution with scale-diverse Mamba-based spatial propagation through an interval-coupled pipeline. In this framework, Neural ODE enables smoother and more consistent feature transformation in the reduced representation space, while the multi-branch Mamba architecture performs efficient long-range spatial propagation and cross-scale context interaction with linear complexity. By unifying continuous feature evolution and efficient spatial propagation, HyperMODE establishes a coherent hybrid paradigm for spectral–spatial representation learning. Extensive experiments on four public HSI benchmarks, including Pavia University, WHU-Hi-HanChuan, WHU-Hi-LongKou, and Houston 2013, demonstrate stable and competitive classification performance, validating the effectiveness of the proposed framework. The source code will be made available at https://github.com/JaylenTang/HyperMODE.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 35755-35772
TriFusion: A Unified CNN-Transformer Framework for Multiscale and Spectral-Spatial Learning in Hyperspectral Image Classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 35755-35772
Open AccessTriFusion: A Unified CNN-Transformer Framework for Multiscale and Spectral-Spatial Learning in Hyperspectral Image Classification
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 21474-21491
HyperMODE: A Continuous-Depth Spectral–Spatial Modeling Framework With Mamba and Neural Ordinary Differential Equations for Hyperspectral Image Classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 21474-21491
Open AccessHyperMODE: A Continuous-Depth Spectral–Spatial Modeling Framework With Mamba and Neural Ordinary Differential Equations for Hyperspectral Image Classification
- Open Access
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. PP (19391404) , 1-15
HyperEAST: An Enhanced Attention-Based Spectral-Spatial Transformer with Self-Supervised Pretraining for Hyperspectral Image Classification
Hyperspectral images (HSIs) are essential in geoscientific applications such as resource exploration, precision agriculture, and environmental monitoring due to their rich spectral-spatial information. However, existing classification methods face notable limitations: PCA ignores spatial context, CNNs lack long-range modeling, and Vision Transformer (ViT)-based models often overfit under label-scarce conditions due to their high capacity and modality-agnostic design. To address these challenges, we propose HyperEAST, an efficient dual-branch ViT framework that explicitly decouples spectral and spatial feature modeling. At its core is a novel Linear Fusion Attention Mechanism (LFAM), which replaces dot-product attention with a softmax-free additive formulation based on lightweight convolutions, enabling local-global representation learning with linear complexity. To enhance robustness under limited labels, we adopt a modality-aware masked image modeling (MIM) strategy that separately reconstructs masked spectral and spatial tokens during self-supervised pretraining. We further introduce a dataset-aware hybrid loss combining cross-entropy and focal loss to mitigate class imbalance and sharpen decision boundaries. Experiments on four benchmark HSI datasets-WHU-Hi-HC, WHU-Hi-LK, Indian Pines, and Pavia University-demonstrate that HyperEAST achieves competitive accuracy, efficiency, and robustness. Code is available at https://github.com/JaylenTang/HyperEAST.
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. PP (19391404) , 1-15
Open AccessHyperEAST: An Enhanced Attention-Based Spectral-Spatial Transformer with Self-Supervised Pretraining for Hyperspectral Image Classification
Hyperspectral images (HSIs) are essential in geoscientific applications such as resource exploration, precision agriculture, and environmental monitoring due to their rich spectral-spatial information. However, existing classification methods face notable limitations: PCA ignores spatial context, CNNs lack long-range modeling, and Vision Transformer (ViT)-based models often overfit under label-scarce conditions due to their high capacity and modality-agnostic design. To address these challenges, we propose HyperEAST, an efficient dual-branch ViT framework that explicitly decouples spectral and spatial feature modeling. At its core is a novel Linear Fusion Attention Mechanism (LFAM), which replaces dot-product attention with a softmax-free additive formulation based on lightweight convolutions, enabling local-global representation learning with linear complexity. To enhance robustness under limited labels, we adopt a modality-aware masked image modeling (MIM) strategy that separately reconstructs masked spectral and spatial tokens during self-supervised pretraining. We further introduce a dataset-aware hybrid loss combining cross-entropy and focal loss to mitigate class imbalance and sharpen decision boundaries. Experiments on four benchmark HSI datasets-WHU-Hi-HC, WHU-Hi-LK, Indian Pines, and Pavia University-demonstrate that HyperEAST achieves competitive accuracy, efficiency, and robustness. Code is available at https://github.com/JaylenTang/HyperEAST.
- 15 July 2025
- Published by Springer Nature
- p. 364-375
HiC-KAN: Hybrid Convolutional Kolmogorov-Arnold Network Architecture for Hyperspectral Image Classification
- 15 July 2025
- Published by Springer Nature
- p. 364-375
HiC-KAN: Hybrid Convolutional Kolmogorov-Arnold Network Architecture for Hyperspectral Image Classification
- Open Access
- 1 April 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (4) , 3064-3083
EMCAH-Net: an effective multi-scale context aggregation hybrid network for medical image segmentation
Background: Pixel-level medical image segmentation tasks are challenging due to factors such as variable target scales, complex geometric shapes, and low contrast. Although U-shaped hybrid networks have demonstrated strong performance, existing models often fail to effectively integrate the local features captured by convolutional neural networks (CNNs) with the global features provided by Transformers. Moreover, their self-attention mechanisms often lack adequate emphasis on critical spatial and channel information. To address these challenges, our goal was to develop a hybrid deep learning model that can effectively and robustly segment medical images, including but not limited to computed tomography (CT) and magnetic resonance (MR) images. Methods: We propose an effective hybrid U-shaped network, named the effective multi-scale context aggregation hybrid network (EMCAH-Net). It integrates an effective multi-scale context aggregation (EMCA) block in the backbone, along with a dual-attention augmented self-attention (DASA) block embedded in the skip connections and bottleneck layers. Aimed at the characteristics of medical images, the former block focuses on fine-grained local multi-scale feature encoding, whereas the latter enhances global representation learning by adaptively combining spatial and channel attention with self-attention. This approach not only effectively integrates local multi-scale and global features but also reinforces skip connections, thereby highlighting segmentation targets and precisely delineating boundaries. The code is publicly available at https://github.com/AloneIsland/EMCAH-Net. Results: Compared to previous state-of-the-art (SOTA) methods, the EMCAH-Net achieves outstanding performance in medical image segmentation, with Dice similarity coefficient (DSC) scores of 84.73% (+2.85), 92.33% (+0.27), and 82.47% (+0.76) on the Synapse, automated cardiac diagnosis challenge (ACDC), and digital retinal images for vessel extraction (DRIVE) datasets, respectively. Additionally, it maintains computational efficiency in terms of model parameters and floating point operations (FLOPs). For instance, EMCAH-Net surpasses TransUNet on the Synapse dataset by 7.25% in DSC while requiring only 25% of the parameters and 71% of the FLOPs. Conclusions: EMCAH-Net has demonstrated significant advantages in segmenting multi-scale, small, and boundary-blurred features in medical images. Extensive experiments on abdominal multi-organ, cardiac, and retinal vessel medical segmentation tasks confirm that EMCAH-Net surpasses previous methods, including pure CNN, pure Transformer, and hybrid architectures.
- 1 April 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (4) , 3064-3083
Open AccessEMCAH-Net: an effective multi-scale context aggregation hybrid network for medical image segmentation
Background: Pixel-level medical image segmentation tasks are challenging due to factors such as variable target scales, complex geometric shapes, and low contrast. Although U-shaped hybrid networks have demonstrated strong performance, existing models often fail to effectively integrate the local features captured by convolutional neural networks (CNNs) with the global features provided by Transformers. Moreover, their self-attention mechanisms often lack adequate emphasis on critical spatial and channel information. To address these challenges, our goal was to develop a hybrid deep learning model that can effectively and robustly segment medical images, including but not limited to computed tomography (CT) and magnetic resonance (MR) images. Methods: We propose an effective hybrid U-shaped network, named the effective multi-scale context aggregation hybrid network (EMCAH-Net). It integrates an effective multi-scale context aggregation (EMCA) block in the backbone, along with a dual-attention augmented self-attention (DASA) block embedded in the skip connections and bottleneck layers. Aimed at the characteristics of medical images, the former block focuses on fine-grained local multi-scale feature encoding, whereas the latter enhances global representation learning by adaptively combining spatial and channel attention with self-attention. This approach not only effectively integrates local multi-scale and global features but also reinforces skip connections, thereby highlighting segmentation targets and precisely delineating boundaries. The code is publicly available at https://github.com/AloneIsland/EMCAH-Net. Results: Compared to previous state-of-the-art (SOTA) methods, the EMCAH-Net achieves outstanding performance in medical image segmentation, with Dice similarity coefficient (DSC) scores of 84.73% (+2.85), 92.33% (+0.27), and 82.47% (+0.76) on the Synapse, automated cardiac diagnosis challenge (ACDC), and digital retinal images for vessel extraction (DRIVE) datasets, respectively. Additionally, it maintains computational efficiency in terms of model parameters and floating point operations (FLOPs). For instance, EMCAH-Net surpasses TransUNet on the Synapse dataset by 7.25% in DSC while requiring only 25% of the parameters and 71% of the FLOPs. Conclusions: EMCAH-Net has demonstrated significant advantages in segmenting multi-scale, small, and boundary-blurred features in medical images. Extensive experiments on abdominal multi-organ, cardiac, and retinal vessel medical segmentation tasks confirm that EMCAH-Net surpasses previous methods, including pure CNN, pure Transformer, and hybrid architectures.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Swin-MSP: A Shifted Windows Masked Spectral Pretraining Model for Hyperspectral Image Classification
Deep Learning has found widespread application in Hyperspectral Image (HSI) classification, where Transformer architectures based on self-attention have emerged as state-of-the-art (SOTA). The Swin-MAE framework utilizes a masked autoencoder approach with Shifted Windows Transformer as its backbone, demonstrating strong representational power and performance. This study proposes a Shifted Windows Masking Spectral Pretraining (Swin-MSP) model, which achieves hierarchical modeling of hyperspectral data from local to global scales by introducing spectral masking pretraining techniques and a hierarchical architecture. To fit with this pretraining, we introduce the Uniaxial Continuous Cross-Correlation Layer (UC3L), a straightforward yet effective solution tailored for hyperspectral imagery masking. And we design the Shift Frequency Band Transformer (SFBT) to hierarchically characterize spectral features. Experiments with publicly available datasets establish that our pretrained network significantly improves classification efficiency compared with SOTA networks. Furthermore, we systematically investigate the sensitivity of various datasets to pretraining hyper-parameters. The results underscore that the universal spectral representation acquired during the pretraining phase serves as a robust initialization for subsequent task-specific fine-tuning. It is noted that this work breaks from traditional ViT approaches, offering a new perspective on hyperspectral dataset pretraining. Code is available at https://github.com/teaRRe/Swin-MSP.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Swin-MSP: A Shifted Windows Masked Spectral Pretraining Model for Hyperspectral Image Classification
Deep Learning has found widespread application in Hyperspectral Image (HSI) classification, where Transformer architectures based on self-attention have emerged as state-of-the-art (SOTA). The Swin-MAE framework utilizes a masked autoencoder approach with Shifted Windows Transformer as its backbone, demonstrating strong representational power and performance. This study proposes a Shifted Windows Masking Spectral Pretraining (Swin-MSP) model, which achieves hierarchical modeling of hyperspectral data from local to global scales by introducing spectral masking pretraining techniques and a hierarchical architecture. To fit with this pretraining, we introduce the Uniaxial Continuous Cross-Correlation Layer (UC3L), a straightforward yet effective solution tailored for hyperspectral imagery masking. And we design the Shift Frequency Band Transformer (SFBT) to hierarchically characterize spectral features. Experiments with publicly available datasets establish that our pretrained network significantly improves classification efficiency compared with SOTA networks. Furthermore, we systematically investigate the sensitivity of various datasets to pretraining hyper-parameters. The results underscore that the universal spectral representation acquired during the pretraining phase serves as a robust initialization for subsequent task-specific fine-tuning. It is noted that this work breaks from traditional ViT approaches, offering a new perspective on hyperspectral dataset pretraining. Code is available at https://github.com/teaRRe/Swin-MSP.
- 3 April 2023
- Published by Elsevier in Internet of Things
- Vol. 22
Max–min distance embedding for unsupervised hyperspectral image classification in the satellite Internet of Things system
- 3 April 2023
- Published by Elsevier in Internet of Things
- Vol. 22
Max–min distance embedding for unsupervised hyperspectral image classification in the satellite Internet of Things system