Xiaoyuan Yang
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
Xiaoyuan Yang has a total of 74 co-authors. Here are the top co-authors by number of shared publications:
- Kangqing Shen
School of Information Network Security, Peoples Public Security University of China, Beijing, China
5 shared publications - Yixiao Li
School of Mathematical Sciences Beihang University China
4 shared publications - Huwei Ren
Beihang Univ, Sch Math Sci, Beijing 102206, Peoples R China
3 shared publications - Ruisheng Qi
School of Mathematics and Statistics Northeastern University at Qinhuangdao Qinhuangdao China
3 shared publications Yinghan Zhang
Department of Mathematics, Beihang University, LMIB of the Ministry of Education, Beijing, China
3 shared publicationsBo Li
Digital Media Laboratory , School of Computer Science and Engineering, Beihang University , Beijing, China
2 shared publications
Latest Publications
- 7 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17  (4) , 180
Trans3DHead: a multi-task transformer for 3D head alignment
- 7 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17  (4) , 180
Trans3DHead: a multi-task transformer for 3D head alignment
- 20 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34  (10577149) , 7728-7743
Perception-Oriented Bidirectional Attention Network for Image Super-Resolution Quality Assessment
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited. In this work, we propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module. First, we encode the input images for feature representations. Inspired by the characteristics of the human visual system, we then construct the perception-oriented PBA module. Specifically, different from existing attention-based SR IQA methods, we conceive a Bidirectional Attention to bidirectionally construct visual attention to distortion, which is consistent with the generation and evaluation processes of SR images. To further guide the quality assessment towards the perception of distorted information, we propose Grouped Multi-scale Deformable Convolution, enabling the proposed method to adaptively perceive distortion. Moreover, we design Sub-information Excitation Convolution to direct visual perception to both sub-pixel and sub-channel attention. Finally, the quality prediction module is exploited to integrate quality-aware features and regress quality scores. Extensive experiments demonstrate that our proposed PBAN outperforms state-of-the-art quality assessment methods.
- 20 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34  (10577149) , 7728-7743
Perception-Oriented Bidirectional Attention Network for Image Super-Resolution Quality Assessment
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited. In this work, we propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module. First, we encode the input images for feature representations. Inspired by the characteristics of the human visual system, we then construct the perception-oriented PBA module. Specifically, different from existing attention-based SR IQA methods, we conceive a Bidirectional Attention to bidirectionally construct visual attention to distortion, which is consistent with the generation and evaluation processes of SR images. To further guide the quality assessment towards the perception of distorted information, we propose Grouped Multi-scale Deformable Convolution, enabling the proposed method to adaptively perceive distortion. Moreover, we design Sub-information Excitation Convolution to direct visual perception to both sub-pixel and sub-channel attention. Finally, the quality prediction module is exploited to integrate quality-aware features and regress quality scores. Extensive experiments demonstrate that our proposed PBAN outperforms state-of-the-art quality assessment methods.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-17
EAMNet: Efficient Adaptive Mamba Network for Infrared Small-Target Detection
Infrared small target detection (ISTD) is essential for various fields. Recent approaches based on existing network structures including convolutional neural networks (CNNs), Transformers, and diffusion models, still face challenges in balancing accuracy and efficiency. To address this problem, this paper proposes an Efficient Adaptive Mamba Network (EAMNet) based on the advanced Mamba structure, which effectively models long-range dependencies while maintaining linear complexity, enabling EAMNet to achieve superior detection performance while significantly improving efficiency. First, a Mamba-based UNet architecture is introduced, which processes separated features in parallel, making it highly efficient with a low parameter count and computational cost. To better adapt the Mamba-based framework to the unique characteristics of infrared images, such as low contrast and small target sizes, we propose an adaptive filter module (AFM) that applies adaptive filtering by predicting filter parameters through an additional designed sub-network, enhancing the boundaries and visibility of infrared targets. To further enhance model performance and ensure efficient feature fusion, we propose a shared adaptive spatial attention module (SASAM), which enables a more compact and efficient feature representation in generating spatial attention maps, while minimizing additional computational overhead. Extensive experiments on public benchmarks demonstrate the effectiveness of the proposed EAMNet in both improving accuracy and efficiency compared to existing state-of-the-art methods. Besides, ablation experiments verify the effectiveness of each module. The code is available at https://github.com/jiangjin1246/EAMNet.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-17
EAMNet: Efficient Adaptive Mamba Network for Infrared Small-Target Detection
Infrared small target detection (ISTD) is essential for various fields. Recent approaches based on existing network structures including convolutional neural networks (CNNs), Transformers, and diffusion models, still face challenges in balancing accuracy and efficiency. To address this problem, this paper proposes an Efficient Adaptive Mamba Network (EAMNet) based on the advanced Mamba structure, which effectively models long-range dependencies while maintaining linear complexity, enabling EAMNet to achieve superior detection performance while significantly improving efficiency. First, a Mamba-based UNet architecture is introduced, which processes separated features in parallel, making it highly efficient with a low parameter count and computational cost. To better adapt the Mamba-based framework to the unique characteristics of infrared images, such as low contrast and small target sizes, we propose an adaptive filter module (AFM) that applies adaptive filtering by predicting filter parameters through an additional designed sub-network, enhancing the boundaries and visibility of infrared targets. To further enhance model performance and ensure efficient feature fusion, we propose a shared adaptive spatial attention module (SASAM), which enables a more compact and efficient feature representation in generating spatial attention maps, while minimizing additional computational overhead. Extensive experiments on public benchmarks demonstrate the effectiveness of the proposed EAMNet in both improving accuracy and efficiency compared to existing state-of-the-art methods. Besides, ablation experiments verify the effectiveness of each module. The code is available at https://github.com/jiangjin1246/EAMNet.
- Open Access
Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited. In this work, we propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module. First, we encode the input images for feature representations. Inspired by the characteristics of the human visual system, we then construct the perception-oriented PBA module. Specifically, different from existing attention-based SR IQA methods, we conceive a Bidirectional Attention to bidirectionally construct visual attention to distortion, which is consistent with the generation and evaluation processes of SR images. To further guide the quality assessment towards the perception of distorted information, we propose Grouped Multi-scale Deformable Convolution, enabling the proposed method to adaptively perceive distortion. Moreover, we design Sub-information Excitation Convolution to direct visual perception to both sub-pixel and sub-channel attention. Finally, the quality prediction module is exploited to integrate quality-aware features and regress quality scores. Extensive experiments demonstrate that our proposed PBAN outperforms state-of-the-art quality assessment methods.
Open AccessPerception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited. In this work, we propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module. First, we encode the input images for feature representations. Inspired by the characteristics of the human visual system, we then construct the perception-oriented PBA module. Specifically, different from existing attention-based SR IQA methods, we conceive a Bidirectional Attention to bidirectionally construct visual attention to distortion, which is consistent with the generation and evaluation processes of SR images. To further guide the quality assessment towards the perception of distorted information, we propose Grouped Multi-scale Deformable Convolution, enabling the proposed method to adaptively perceive distortion. Moreover, we design Sub-information Excitation Convolution to direct visual perception to both sub-pixel and sub-channel attention. Finally, the quality prediction module is exploited to integrate quality-aware features and regress quality scores. Extensive experiments demonstrate that our proposed PBAN outperforms state-of-the-art quality assessment methods.
- 28 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-14
Cross-Modal Contrastive Pansharpening via Uncertainty Guidance
Deep learning-based pansharpening has been widely applied in high-resolution imaging. Yet, artifacts related to generalization and over-smoothing have continuously been the challenge, primarily due to the mismatch between the simulation dataset and the unseen real-world scenarios. Current approaches address these through unsupervised frameworks or generative models, while modal inconsistency are not fully considered, leading to suboptimal performance. In this paper, we propose a contrastive cross-modal framework via uncertainty guidance (UGCC), which comprises of three key modules: a contrast feature enhancement module (CFEM), a cross-modal compensation module (CMCM) and an uncertainty guidance module (UGM). Firstly, to enhance generalization and reduce over-fitting, CFEM is introduced. Robust contrast features are augmented and learned sparsely in latent space, where sample distributions are refined, and redundant information is filtered from highly similar sample pairs for enhanced training stability. Furthermore, CMCM mitigates modal inconsistency effectively by domain transfer and collaborative attention, achieving efficient modal separation and interaction. Finally, to adaptively balancing the performance of CMCM and CFEM based on prediction confidence, a hybrid loss function is designed, where UGM adjusts the weights through quantifying statistical-versus-structural uncertainties. Extensive experiments on Quickbird, Gaofen-2, WorldView-2, and WorldView-3 demonstrate that the performance of the proposed method surpasses or matches the state of arts. Furthermore, ablation studies validate the effectiveness of each component. The code is now available at: https://github.com/meimeizeng/UGCF.
- 28 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-14
Cross-Modal Contrastive Pansharpening via Uncertainty Guidance
Deep learning-based pansharpening has been widely applied in high-resolution imaging. Yet, artifacts related to generalization and over-smoothing have continuously been the challenge, primarily due to the mismatch between the simulation dataset and the unseen real-world scenarios. Current approaches address these through unsupervised frameworks or generative models, while modal inconsistency are not fully considered, leading to suboptimal performance. In this paper, we propose a contrastive cross-modal framework via uncertainty guidance (UGCC), which comprises of three key modules: a contrast feature enhancement module (CFEM), a cross-modal compensation module (CMCM) and an uncertainty guidance module (UGM). Firstly, to enhance generalization and reduce over-fitting, CFEM is introduced. Robust contrast features are augmented and learned sparsely in latent space, where sample distributions are refined, and redundant information is filtered from highly similar sample pairs for enhanced training stability. Furthermore, CMCM mitigates modal inconsistency effectively by domain transfer and collaborative attention, achieving efficient modal separation and interaction. Finally, to adaptively balancing the performance of CMCM and CFEM based on prediction confidence, a hybrid loss function is designed, where UGM adjusts the weights through quantifying statistical-versus-structural uncertainties. Extensive experiments on Quickbird, Gaofen-2, WorldView-2, and WorldView-3 demonstrate that the performance of the proposed method surpasses or matches the state of arts. Furthermore, ablation studies validate the effectiveness of each component. The code is now available at: https://github.com/meimeizeng/UGCF.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22  (1545598X) , 1-5
IcGAN4ColSAR: A Novel Multispectral Conditional Generative Adversarial Network Approach for SAR Image Colorization
SAR colorization aims to enrich gray-scale SAR images with color while ensuring the preservation of original radiometric and spatial details. However, researchers often limit themselves to using only the red, green, and blue bands of a multispectral image as the source of color information, coupled with a single polarization channel from the SAR image. This approach neglects the intrinsic characteristics of remote sensing data and thus fails to fully leverage available information. To overcome this limitation, this research attempts to explore inclusion of all available bands from multispectral images along with dual polarization channels from SAR imagery in the colorization process. Furthermore, we present a new colorization method called improved conditional generative adversarial network for SAR colorization (IcGAN4ColSAR). This method tries to include the spectral angle mapper index within its loss function. Sufficient experiments show that our explorations in the number of data channels and the loss function are helpful in improving the colorization performance of the SAR image.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22  (1545598X) , 1-5
IcGAN4ColSAR: A Novel Multispectral Conditional Generative Adversarial Network Approach for SAR Image Colorization
SAR colorization aims to enrich gray-scale SAR images with color while ensuring the preservation of original radiometric and spatial details. However, researchers often limit themselves to using only the red, green, and blue bands of a multispectral image as the source of color information, coupled with a single polarization channel from the SAR image. This approach neglects the intrinsic characteristics of remote sensing data and thus fails to fully leverage available information. To overcome this limitation, this research attempts to explore inclusion of all available bands from multispectral images along with dual polarization channels from SAR imagery in the colorization process. Furthermore, we present a new colorization method called improved conditional generative adversarial network for SAR colorization (IcGAN4ColSAR). This method tries to include the spectral angle mapper index within its loss function. Sufficient experiments show that our explorations in the number of data channels and the loss function are helpful in improving the colorization performance of the SAR image.
- Open Access
Deep Bi-directional Attention Network for Image Super-Resolution Quality Assessment
There has emerged a growing interest in exploring efficient quality assessment algorithms for image super-resolution (SR). However, employing deep learning techniques, especially dual-branch algorithms, to automatically evaluate the visual quality of SR images remains challenging. Existing SR image quality assessment (IQA) metrics based on two-stream networks lack interactions between branches. To address this, we propose a novel full-reference IQA (FR-IQA) method for SR images. Specifically, producing SR images and evaluating how close the SR images are to the corresponding HR references are separate processes. Based on this consideration, we construct a deep Bi-directional Attention Network (BiAtten-Net) that dynamically deepens visual attention to distortions in both processes, which aligns well with the human visual system (HVS). Experiments on public SR quality databases demonstrate the superiority of our proposed BiAtten-Net over state-of-the-art quality assessment methods. In addition, the visualization results and ablation study show the effectiveness of bi-directional attention.
Open AccessDeep Bi-directional Attention Network for Image Super-Resolution Quality Assessment
There has emerged a growing interest in exploring efficient quality assessment algorithms for image super-resolution (SR). However, employing deep learning techniques, especially dual-branch algorithms, to automatically evaluate the visual quality of SR images remains challenging. Existing SR image quality assessment (IQA) metrics based on two-stream networks lack interactions between branches. To address this, we propose a novel full-reference IQA (FR-IQA) method for SR images. Specifically, producing SR images and evaluating how close the SR images are to the corresponding HR references are separate processes. Based on this consideration, we construct a deep Bi-directional Attention Network (BiAtten-Net) that dynamically deepens visual attention to distortions in both processes, which aligns well with the human visual system (HVS). Experiments on public SR quality databases demonstrate the superiority of our proposed BiAtten-Net over state-of-the-art quality assessment methods. In addition, the visualization results and ablation study show the effectiveness of bi-directional attention.
- 8 November 2023
- Published by Elsevier in Neural Networks
- Vol. 169, 698-712
A benchmarking protocol for SAR colorization: From regression to deep learning approaches
- 8 November 2023
- Published by Elsevier in Neural Networks
- Vol. 169, 698-712
A benchmarking protocol for SAR colorization: From regression to deep learning approaches
- Open Access
A Benchmarking Protocol for SAR Colorization: From Regression to Deep Learning Approaches
Synthetic aperture radar (SAR) images are widely used in remote sensing. Interpreting SAR images can be challenging due to their intrinsic speckle noise and grayscale nature. To address this issue, SAR colorization has emerged as a research direction to colorize gray scale SAR images while preserving the original spatial information and radiometric information. However, this research field is still in its early stages, and many limitations can be highlighted. In this paper, we propose a full research line for supervised learning-based approaches to SAR colorization. Our approach includes a protocol for generating synthetic color SAR images, several baselines, and an effective method based on the conditional generative adversarial network (cGAN) for SAR colorization. We also propose numerical assessment metrics for the problem at hand. To our knowledge, this is the first attempt to propose a research line for SAR colorization that includes a protocol, a benchmark, and a complete performance evaluation. Our extensive tests demonstrate the effectiveness of our proposed cGAN-based network for SAR colorization. The code will be made publicly available.
Open AccessA Benchmarking Protocol for SAR Colorization: From Regression to Deep Learning Approaches
Synthetic aperture radar (SAR) images are widely used in remote sensing. Interpreting SAR images can be challenging due to their intrinsic speckle noise and grayscale nature. To address this issue, SAR colorization has emerged as a research direction to colorize gray scale SAR images while preserving the original spatial information and radiometric information. However, this research field is still in its early stages, and many limitations can be highlighted. In this paper, we propose a full research line for supervised learning-based approaches to SAR colorization. Our approach includes a protocol for generating synthetic color SAR images, several baselines, and an effective method based on the conditional generative adversarial network (cGAN) for SAR colorization. We also propose numerical assessment metrics for the problem at hand. To our knowledge, this is the first attempt to propose a research line for SAR colorization that includes a protocol, a benchmark, and a complete performance evaluation. Our extensive tests demonstrate the effectiveness of our proposed cGAN-based network for SAR colorization. The code will be made publicly available.
- 3 June 2023
- Published by Elsevier in Neural Networks
- Vol. 165, 358-369
Adversarial feature hybrid framework for steganography with shifted window local loss
- 3 June 2023
- Published by Elsevier in Neural Networks
- Vol. 165, 358-369
Adversarial feature hybrid framework for steganography with shifted window local loss