Ruifan Zhang
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
Ruifan Zhang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Gongping Yang
Shandong University
6 shared publications - Yikun Liu
Shandong Management University
5 shared publications - Hao Wang
School of Software, Shandong University, Jinan, China
4 shared publications - Mingyao Feng
School of Software, Shandong University, Jinan, China
4 shared publications - Hai-Miao Hu
Beijing Key Laboratory of Digital Media, School of Computer Science and Engineering, Beihang University, Beijing, China
3 shared publications - Mingsong Li
School of Software, Shandong University, Jinan, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14674-14683
Fantasy Anything: A Journey of Outlier Imagination Across Unknown Spaces
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14674-14683
Open AccessFantasy Anything: A Journey of Outlier Imagination Across Unknown Spaces
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7152-7167
A Multi-Category Anomaly Editing Network With Correlation Exploration and Voxel-Level Attention for Unsupervised Surface Anomaly Detection
Developing a unified model for surface anomaly detection remains challenging due to significant variations across product categories. Recent feature editing methods, as a branch of image reconstruction, mitigate the over-generalization of auto-encoders that leads to accurate anomaly reconstruction. However, these methods are only suited for texture-category products and have significant limitations in being generalized to other categories. In this article, we propose a multi-category anomaly editing network with a dual-branch training approach: one branch processes defect-free images (normal branch), while the other handles synthetic anomaly images (anomaly branch). Specifically, the paired samples are first fed into the multi-category anomaly feature editing based auto-encoder (MCAFE-AE) to perform image reconstruction and inpainting. In the normal branch, we propose a dual-entropy constrained deep embedded clustering module (DEC-DECM) to promote a more compact and orderly distribution of normal latent features, while avoiding trivial clustering solutions. Based on the clustering results, we further design a patch-based adaptive thresholding (PAT) strategy to adaptively calculate the threshold representing the central boundary of the cluster center for each local patch, thereby enabling the model to detect anomalies. Then, in the anomaly branch, we propose a multi-category anomaly feature editing module (MCAFEM) to identify anomalies in synthetic images and apply a category-oriented feature editing strategy to transform detected anomaly features into normal ones, thereby suppressing the reconstruction of anomalies. After completing the image reconstruction and inpainting, the input images from both branches and their respective output images are concatenated and fed into the correlation exploration and voxel-level attention based prediction network (CEVA-Net) for anomaly segmentation. The network is integrated with our proposed correlation-dependency exploration and voxel-level attention refinement module (CDE-VARM) and generates precise anomaly maps under the guidance of the bidirectional-path feature fusion (BPFF) and deep supervised learning (DSL). Extensive experiments on three datasets show that our method achieves state-of-the-art performance.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7152-7167
A Multi-Category Anomaly Editing Network With Correlation Exploration and Voxel-Level Attention for Unsupervised Surface Anomaly Detection
Developing a unified model for surface anomaly detection remains challenging due to significant variations across product categories. Recent feature editing methods, as a branch of image reconstruction, mitigate the over-generalization of auto-encoders that leads to accurate anomaly reconstruction. However, these methods are only suited for texture-category products and have significant limitations in being generalized to other categories. In this article, we propose a multi-category anomaly editing network with a dual-branch training approach: one branch processes defect-free images (normal branch), while the other handles synthetic anomaly images (anomaly branch). Specifically, the paired samples are first fed into the multi-category anomaly feature editing based auto-encoder (MCAFE-AE) to perform image reconstruction and inpainting. In the normal branch, we propose a dual-entropy constrained deep embedded clustering module (DEC-DECM) to promote a more compact and orderly distribution of normal latent features, while avoiding trivial clustering solutions. Based on the clustering results, we further design a patch-based adaptive thresholding (PAT) strategy to adaptively calculate the threshold representing the central boundary of the cluster center for each local patch, thereby enabling the model to detect anomalies. Then, in the anomaly branch, we propose a multi-category anomaly feature editing module (MCAFEM) to identify anomalies in synthetic images and apply a category-oriented feature editing strategy to transform detected anomaly features into normal ones, thereby suppressing the reconstruction of anomalies. After completing the image reconstruction and inpainting, the input images from both branches and their respective output images are concatenated and fed into the correlation exploration and voxel-level attention based prediction network (CEVA-Net) for anomaly segmentation. The network is integrated with our proposed correlation-dependency exploration and voxel-level attention refinement module (CDE-VARM) and generates precise anomaly maps under the guidance of the bidirectional-path feature fusion (BPFF) and deep supervised learning (DSL). Extensive experiments on three datasets show that our method achieves state-of-the-art performance.
- Open Access
- 13 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 15427-15441
Consistency Preserved Nonuniform Scattering Removal for Wide-Swath Remote Sensing Images
Removal of haze and thin clouds in remote sensing images has been extensively studied, leading to the development of effective methods. However, when applied to wide-swath images, conventional dehazing approaches often generate patch-level inconsistencies during combination. To address the issue, this paper presents a consistency preserved scattering model designed with multiple features to remove haze and thin cloud effects. Specifically, three modules named ESD, ILM and SPC are introduced to improve the basic prior-based dehazing method. ESD focuses on cloud area exclusion to ensure accurate estimation with the scattering distribution map. ILM is based on the linear relationship with scattering distribution and illumination, aiming to smooth the global illumination. SPC addresses the spectral adaptation issues in wide-swath scenes. Experimental results indicate that, compared to state-of-the-art methods, the proposed model and method effectively restores textural details in remote sensing imagery affected by heterogeneous haze, while resolving cross-patch inconsistency to enhance overall image coherence and interpretability.
- 13 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 15427-15441
Open AccessConsistency Preserved Nonuniform Scattering Removal for Wide-Swath Remote Sensing Images
Removal of haze and thin clouds in remote sensing images has been extensively studied, leading to the development of effective methods. However, when applied to wide-swath images, conventional dehazing approaches often generate patch-level inconsistencies during combination. To address the issue, this paper presents a consistency preserved scattering model designed with multiple features to remove haze and thin cloud effects. Specifically, three modules named ESD, ILM and SPC are introduced to improve the basic prior-based dehazing method. ESD focuses on cloud area exclusion to ensure accurate estimation with the scattering distribution map. ILM is based on the linear relationship with scattering distribution and illumination, aiming to smooth the global illumination. SPC addresses the spectral adaptation issues in wide-swath scenes. Experimental results indicate that, compared to state-of-the-art methods, the proposed model and method effectively restores textural details in remote sensing imagery affected by heterogeneous haze, while resolving cross-patch inconsistency to enhance overall image coherence and interpretability.
- Open Access
- 4 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 160-175
Laplacian Pyramid Network With Hybrid Encoder and Edge Guidance for Remote Sensing Change Detection
Remote sensing change detection (CD) is a crucial task for observing and analyzing dynamic land cover alterations. Many CD methods based on deep learning demonstrate strong performance, but their effectiveness is influenced by the choice of encoder and the challenge of accurately delineating the edges of change regions. In this article, we propose a Laplacian pyramid network with hybrid encoder and edge guidance (HE-LPNet) to solve these issues. Specifically, the hybrid encoder combines the advantages of convolutional neural networks and transformer, resulting in extracted features that are more fine-grained. Meanwhile, the hybrid encoder incorporates the vision foundation models, leading to enhanced generalization of the overall model. In addition to feature extraction, the image is processed to generate a Laplacian pyramid, which is then fused with the features extracted by the hybrid encoder to enhance the salient features at the pixel-level. In the decoder stage, weighted guided attention is designed to selectively apply channel and spatial attention to the fused features, improving the network's ability to discriminate change regions. Furthermore, we present an edge-guided loss to capture edge information in change regions. To validate the effectiveness of the proposed HE-LPNet, extensive experiments are conducted on three high-resolution remote sensing CD datasets. The experimental results demonstrate that our method surpasses other state-of-the-art CD methods.
- 4 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 160-175
Open AccessLaplacian Pyramid Network With Hybrid Encoder and Edge Guidance for Remote Sensing Change Detection
Remote sensing change detection (CD) is a crucial task for observing and analyzing dynamic land cover alterations. Many CD methods based on deep learning demonstrate strong performance, but their effectiveness is influenced by the choice of encoder and the challenge of accurately delineating the edges of change regions. In this article, we propose a Laplacian pyramid network with hybrid encoder and edge guidance (HE-LPNet) to solve these issues. Specifically, the hybrid encoder combines the advantages of convolutional neural networks and transformer, resulting in extracted features that are more fine-grained. Meanwhile, the hybrid encoder incorporates the vision foundation models, leading to enhanced generalization of the overall model. In addition to feature extraction, the image is processed to generate a Laplacian pyramid, which is then fused with the features extracted by the hybrid encoder to enhance the salient features at the pixel-level. In the decoder stage, weighted guided attention is designed to selectively apply channel and spatial attention to the fused features, improving the network's ability to discriminate change regions. Furthermore, we present an edge-guided loss to capture edge information in change regions. To validate the effectiveness of the proposed HE-LPNet, extensive experiments are conducted on three high-resolution remote sensing CD datasets. The experimental results demonstrate that our method surpasses other state-of-the-art CD methods.
- 17 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (7) , 9393-9403
Dual-Constraint Autoencoder and Adaptive Weighted Similarity Spatial Attention for Unsupervised Anomaly Detection
Image reconstruction-based methods with autoencoder have been widely used for unsupervised anomaly detection. By training the reconstruction on normal samples, autoencoder is supposed to produce higher reconstruction error for anomalous samples, which is used as an indicator for detecting anomalies. However, since autoencoder adopts the bottleneck layer to reconstruct data, it is hard to control its generalization capability. When the generalization capability is high, anomalous features can be confused with normal features, resulting in accurate reconstruction of anomalous regions as well. In this article, we propose a dual-constraint autoencoder to alleviate the problem of feature confusion through the dual constraint of adversarial learning and global memory bank. Given a sample pair consisting of a normal sample and a synthetic anomaly sample generated from it as input, the proposed autoencoder first forces the encoding of the synthetic anomaly image to be close to the normal encoding by adversarial learning. Then, the synthetic anomaly encoding is rerepresented with items in memory bank, which records normal features that facilitate image restoration, and the new feature is fed to the decoder for image inpainting. Under such constraints, the generalization capability of the autoencoder is suppressed and will not reconstruct the anomaly region well. After that, we feed the synthetic anomaly image together with the repaired image into the proposed adaptive weighted similarity spatial attention-based U-Net and produce an accurate anomaly map with the help of our proposed adaptive weighted similarity spatial attention. Results on the a comprehensive real-world dataset for unsupervised anomaly detection (MVTec AD) dataset and the beanTech anomaly detection dataset dataset show that our framework achieves state-of-the-art performance.
- 17 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (7) , 9393-9403
Dual-Constraint Autoencoder and Adaptive Weighted Similarity Spatial Attention for Unsupervised Anomaly Detection
Image reconstruction-based methods with autoencoder have been widely used for unsupervised anomaly detection. By training the reconstruction on normal samples, autoencoder is supposed to produce higher reconstruction error for anomalous samples, which is used as an indicator for detecting anomalies. However, since autoencoder adopts the bottleneck layer to reconstruct data, it is hard to control its generalization capability. When the generalization capability is high, anomalous features can be confused with normal features, resulting in accurate reconstruction of anomalous regions as well. In this article, we propose a dual-constraint autoencoder to alleviate the problem of feature confusion through the dual constraint of adversarial learning and global memory bank. Given a sample pair consisting of a normal sample and a synthetic anomaly sample generated from it as input, the proposed autoencoder first forces the encoding of the synthetic anomaly image to be close to the normal encoding by adversarial learning. Then, the synthetic anomaly encoding is rerepresented with items in memory bank, which records normal features that facilitate image restoration, and the new feature is fed to the decoder for image inpainting. Under such constraints, the generalization capability of the autoencoder is suppressed and will not reconstruct the anomaly region well. After that, we feed the synthetic anomaly image together with the repaired image into the proposed adaptive weighted similarity spatial attention-based U-Net and produce an accurate anomaly map with the help of our proposed adaptive weighted similarity spatial attention. Results on the a comprehensive real-world dataset for unsupervised anomaly detection (MVTec AD) dataset and the beanTech anomaly detection dataset dataset show that our framework achieves state-of-the-art performance.
- Open Access
- 10 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 8477-8489
Two-Level Feature Fusion Network for Remote Sensing Image Change Detection
With the advancement of satellite technology, the application space of change detection (CD) in remote sensing images is continuously expanding. However, the development of satellite remote sensing technology is still ongoing, and limited resolution and complex ground object information remain significant challenges in the field of CD. Recent CD networks generally utilize multifeature fusion to make full use of detailed information at different scales. However, most networks have limited capabilities in handling large-scale feature maps, leading to an impact on the effectiveness in detecting detailed information. In this article, we propose a two-level feature fusion CD network that enhances the semantic information contained in large-scale difference feature through a combination of convolutional neural network and transformer-based feature fusion structures. Leveraging a simple backbone network (ResNet-18) to extract dual-temporal feature maps, our model achieves better performance to mainstream state-of-the-art networks. On the LEVIR-CD, WHU-CD, and SYSU-CD datasets, we obtain F1 scores of 92.03%/92.73%/83.25%, intersection over union of 85.24%/86.45%/71.31%, and Kappa coefficient ( $\kappa$ ) of 91.61%/92.45%/78.26%, respectively.
- 10 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 8477-8489
Open AccessTwo-Level Feature Fusion Network for Remote Sensing Image Change Detection
With the advancement of satellite technology, the application space of change detection (CD) in remote sensing images is continuously expanding. However, the development of satellite remote sensing technology is still ongoing, and limited resolution and complex ground object information remain significant challenges in the field of CD. Recent CD networks generally utilize multifeature fusion to make full use of detailed information at different scales. However, most networks have limited capabilities in handling large-scale feature maps, leading to an impact on the effectiveness in detecting detailed information. In this article, we propose a two-level feature fusion CD network that enhances the semantic information contained in large-scale difference feature through a combination of convolutional neural network and transformer-based feature fusion structures. Leveraging a simple backbone network (ResNet-18) to extract dual-temporal feature maps, our model achieves better performance to mainstream state-of-the-art networks. On the LEVIR-CD, WHU-CD, and SYSU-CD datasets, we obtain F1 scores of 92.03%/92.73%/83.25%, intersection over union of 85.24%/86.45%/71.31%, and Kappa coefficient ( $\kappa$ ) of 91.61%/92.45%/78.26%, respectively.
- 1 January 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 18 (01) , 016513-18
Multilevel feature aggregation and enhancement network for remote sensing change detection
Remote sensing change detection refers to the process of identifying and extracting changes in objects within the same geographical region over multiple periods. With the increasing spatial resolution of remote sensing images, the detection of minor changes has become a challenging task. We introduce a multilevel feature aggregation and enhancement network to tackle this issue. Specifically, we propose a multilevel feature aggregation module to aggregate the distinct features extracted from each image, which strengthens the feature representation capability. Subsequently, a difference parallel mapping module is designed to perceive information at different scales by refining the fused features. In addition, our guided change enhancement module captures local and long-range dependencies in multilevel features, improving the network’s accuracy in identifying changing regions. Based on a basic shared weight Siamese backbone without complex structures, our model outperforms other state-of-the-art methods on three datasets in terms of both efficiency and effectiveness.
- 1 January 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 18 (01) , 016513-18
Multilevel feature aggregation and enhancement network for remote sensing change detection
Remote sensing change detection refers to the process of identifying and extracting changes in objects within the same geographical region over multiple periods. With the increasing spatial resolution of remote sensing images, the detection of minor changes has become a challenging task. We introduce a multilevel feature aggregation and enhancement network to tackle this issue. Specifically, we propose a multilevel feature aggregation module to aggregate the distinct features extracted from each image, which strengthens the feature representation capability. Subsequently, a difference parallel mapping module is designed to perceive information at different scales by refining the fused features. In addition, our guided change enhancement module captures local and long-range dependencies in multilevel features, improving the network’s accuracy in identifying changing regions. Based on a basic shared weight Siamese backbone without complex structures, our model outperforms other state-of-the-art methods on three datasets in terms of both efficiency and effectiveness.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Global Context-Based Self-Similarity Feature Augmentation and Bidirectional Feature Fusion for Surface Defect Detection
Surface defect detection is a significant step in industrial production, which is also essential for ensuring the quality of industrial products. At the moment, although the defect detection methods based on computer vision have made great progress, they are still tough to automate the detection due to the challenges of large changes in size, low contrast, strong background interference, large intraclass difference as well as small interclass difference. To address the above issues, we design a deep learning model that mainly consists of a feature augmentation module (FAM), and a multiscale bidirectional feature fusion module (MBFFM), while introducing deformable convolutions into the backbone. The FAM enhances the defect features and magnifies the feature difference between defects and background by combining global context-based self-similarity and spatial attention, which can improve the detection performance for weak defects. The MBFFM is applied to complete the bidirectional fusion of high-level and low-level features for the overall perception of defects. In addition, we design an edge weight loss (EWL) to emphasize defect regions by increasing their weights in the loss. At the same time, by combining EWL and deformable convolution, the backbone can accurately extract comprehensive and complete defect features. Experiments verify that the mean Intersection over Union (mIoU) of our method on the four datasets is superior to other state-of-the-art methods (MT, miou of 83.75%; NEU_SEG, miou of 88.84%; DAGM_defect, miou of 86.74%; ROAD, miou of 76.71%).
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Global Context-Based Self-Similarity Feature Augmentation and Bidirectional Feature Fusion for Surface Defect Detection
Surface defect detection is a significant step in industrial production, which is also essential for ensuring the quality of industrial products. At the moment, although the defect detection methods based on computer vision have made great progress, they are still tough to automate the detection due to the challenges of large changes in size, low contrast, strong background interference, large intraclass difference as well as small interclass difference. To address the above issues, we design a deep learning model that mainly consists of a feature augmentation module (FAM), and a multiscale bidirectional feature fusion module (MBFFM), while introducing deformable convolutions into the backbone. The FAM enhances the defect features and magnifies the feature difference between defects and background by combining global context-based self-similarity and spatial attention, which can improve the detection performance for weak defects. The MBFFM is applied to complete the bidirectional fusion of high-level and low-level features for the overall perception of defects. In addition, we design an edge weight loss (EWL) to emphasize defect regions by increasing their weights in the loss. At the same time, by combining EWL and deformable convolution, the backbone can accurately extract comprehensive and complete defect features. Experiments verify that the mean Intersection over Union (mIoU) of our method on the four datasets is superior to other state-of-the-art methods (MT, miou of 83.75%; NEU_SEG, miou of 88.84%; DAGM_defect, miou of 86.74%; ROAD, miou of 76.71%).
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
JRCC-Net: A Segmentation Network With Joint Representation and Contrast Clustering for Surface Anomaly Detection
The goal of unsupervised surface anomaly detection is to detect areas of the image that are different from the normal pattern, which can be considered as a semantic segmentation problem oriented to anomalous patterns. However, this problem is challenging due to the lack of actual available anomaly samples. In this paper, we transform unsupervised anomaly detection into a self-supervised problem by the proposed anomaly simulation strategy. Using only normal samples for training, real anomalies appearing in the inference phase can be detected. Thus, we propose a segmentation network with joint representation and contrast clustering (JRCC-Net). The proposed method learns a joint representation between simulated samples and the magnitude of the differences in distance from their nearest memory samples, as well as a decision boundary between normal and anomalous samples. Moreover, we propose a novel contrast clustering based representation learning strategy, which allows the model to better learn general patterns from normal samples and mine the latent differences between simulated anomalous and normal samples. JRCC-Net is able to locate anomalies directly in an end-to-end manner and can be trained well with our elaborate anomaly simulation strategy. On the challenging MVTec AD dataset, JRCC-Net outperforms the state-of-the-art unsupervised methods, achieving 98.2 % image-level AUROC and 97.7 % pixel-level AUROC, respectively, and even on the extensively used DAGM dataset, its localization accuracy greatly exceeds that of fully-supervised methods.
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
JRCC-Net: A Segmentation Network With Joint Representation and Contrast Clustering for Surface Anomaly Detection
The goal of unsupervised surface anomaly detection is to detect areas of the image that are different from the normal pattern, which can be considered as a semantic segmentation problem oriented to anomalous patterns. However, this problem is challenging due to the lack of actual available anomaly samples. In this paper, we transform unsupervised anomaly detection into a self-supervised problem by the proposed anomaly simulation strategy. Using only normal samples for training, real anomalies appearing in the inference phase can be detected. Thus, we propose a segmentation network with joint representation and contrast clustering (JRCC-Net). The proposed method learns a joint representation between simulated samples and the magnitude of the differences in distance from their nearest memory samples, as well as a decision boundary between normal and anomalous samples. Moreover, we propose a novel contrast clustering based representation learning strategy, which allows the model to better learn general patterns from normal samples and mine the latent differences between simulated anomalous and normal samples. JRCC-Net is able to locate anomalies directly in an end-to-end manner and can be trained well with our elaborate anomaly simulation strategy. On the challenging MVTec AD dataset, JRCC-Net outperforms the state-of-the-art unsupervised methods, achieving 98.2 % image-level AUROC and 97.7 % pixel-level AUROC, respectively, and even on the extensively used DAGM dataset, its localization accuracy greatly exceeds that of fully-supervised methods.