Yunxin Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yunxin Liu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Danqing Liu
3 shared publicationsGuanliang Wan
School of Artificial Intelligence, Shandong Womens University, Jinan, China
2 shared publicationsTengyue Yang
School of Artificial Intelligence, Shandong Womens University, Jinan, China
2 shared publications- Yanhui Guo
School of Artificial Intelligence, Shandong Womens University, Jinan, China
2 shared publications Jiaxin Li
1 shared publicationQinfen Wang
1 shared publication
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
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 17434-17453
S2CaT: Spatial–Spectral-Based CNN and Transformer Network for Hyperspectral Image Classification
Recent advancements in the field of hyperspectral image (HSI) analysis have highlighted the potential of hybrid architectures that integrate convolutional neural networks (CNNs) with Transformer modules. These architectures are capable of effectively modeling global dependencies while preserving local feature representations. However, these methods fail to fully exploit the joint spatial–spectral features of HSI and instead extract only local or global features separately through CNNs or Transformers. To address these limitations, we propose a novel spatial–spectral-based CNN and Transformer network named S2CaT. In the early stage of the network, dedicated Spatial–Spectral Extractor (SSE) are employed to capture joint spatial and spectral features. Specifically, the Grouped Multi-Scale Spectral Extraction (GMSpe) is responsible for band-wise spectral processing, while the Cascade Spatial Extraction (CaSpa) extracts continuous spatial representations by aggregating multi-level spatial information. Subsequently, we introduce the CaT Fusion module to capture both local and global spectral contextual dependencies. This module comprises two key components: the Dilated Scale CNN (DS CNN) and the Domain Enhanced Transformer (DE Transformer). DS CNN leverages dilated convolutions with varying receptive fields to extract local features and enhance sensitivity to fine-grained textures. The DE Transformer replaces traditional linear projections with channel reorganization for generating the QKV matrices. Channel and spatial attention mechanisms are applied to the Q matrix to enrich feature diversity, while downsampling is introduced in the K and V matrices to suppress noise bands, facilitating robust feature aggregation and cross-domain interaction. We conducted experiments on the Indian Pines, Pavia University, Houston2013, and WHU-Hi-LongKou datasets using 5%, 0.7%, 5%, and 0.1% of the labeled data for training, respectively. The proposed method achieved improvements in average accuracy of at least 0.52%, 1.48%, 0.96%, and 1.07% over several recent state-of-the-art (SOTA) approaches on the corresponding datasets. We have released the full source code to ensure reproducibility. It is available at: https://github.com/ZH3nGsQ/S2CaT.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 17434-17453
Open AccessS2CaT: Spatial–Spectral-Based CNN and Transformer Network for Hyperspectral Image Classification
Recent advancements in the field of hyperspectral image (HSI) analysis have highlighted the potential of hybrid architectures that integrate convolutional neural networks (CNNs) with Transformer modules. These architectures are capable of effectively modeling global dependencies while preserving local feature representations. However, these methods fail to fully exploit the joint spatial–spectral features of HSI and instead extract only local or global features separately through CNNs or Transformers. To address these limitations, we propose a novel spatial–spectral-based CNN and Transformer network named S2CaT. In the early stage of the network, dedicated Spatial–Spectral Extractor (SSE) are employed to capture joint spatial and spectral features. Specifically, the Grouped Multi-Scale Spectral Extraction (GMSpe) is responsible for band-wise spectral processing, while the Cascade Spatial Extraction (CaSpa) extracts continuous spatial representations by aggregating multi-level spatial information. Subsequently, we introduce the CaT Fusion module to capture both local and global spectral contextual dependencies. This module comprises two key components: the Dilated Scale CNN (DS CNN) and the Domain Enhanced Transformer (DE Transformer). DS CNN leverages dilated convolutions with varying receptive fields to extract local features and enhance sensitivity to fine-grained textures. The DE Transformer replaces traditional linear projections with channel reorganization for generating the QKV matrices. Channel and spatial attention mechanisms are applied to the Q matrix to enrich feature diversity, while downsampling is introduced in the K and V matrices to suppress noise bands, facilitating robust feature aggregation and cross-domain interaction. We conducted experiments on the Indian Pines, Pavia University, Houston2013, and WHU-Hi-LongKou datasets using 5%, 0.7%, 5%, and 0.1% of the labeled data for training, respectively. The proposed method achieved improvements in average accuracy of at least 0.52%, 1.48%, 0.96%, and 1.07% over several recent state-of-the-art (SOTA) approaches on the corresponding datasets. We have released the full source code to ensure reproducibility. It is available at: https://github.com/ZH3nGsQ/S2CaT.