Xiaoya 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
Xiaoya Zhang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Wei Peng
Defense Innovation Institute, Chinese Academy of Military Science Intelligent Game and Decision Laboratory, Beijing, China
5 shared publications - Weien Zhou
Intelligent Game and Decision Laboratory, Beijing, China
5 shared publications - Wen Yao
Defense Innovation Institute, Chinese Academy of Military Science, Beijing, China
5 shared publications - Hui Zhang
Department of Mathematics, National University of Defense Technology, Changsha, China
4 shared publications - Jialiang Sun
Chinese Academy of Military Science Beijing China
3 shared publications - Lizhi Cheng
Department of Mathematics National University of Defense Technology 410073 Changsha Hunan China
3 shared publications
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1462-1470
CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1462-1470
Open AccessCDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors
- 29 March 2023
- Published by Springer Nature in Annals of Operations Research
- Vol. 348 (1) , 345-371
Heat source layout optimization using automatic deep learning surrogate and multimodal neighborhood search algorithm
- 29 March 2023
- Published by Springer Nature in Annals of Operations Research
- Vol. 348 (1) , 345-371
Heat source layout optimization using automatic deep learning surrogate and multimodal neighborhood search algorithm
- Open Access
- 17 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 408-412
A Method for Flow Field Reconstruction based on Fourier Neural Operator Network
- 17 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 408-412
Open AccessA Method for Flow Field Reconstruction based on Fourier Neural Operator Network
- Open Access
Physics-Informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites
The rapid analysis of thermal stress and deformation plays a pivotal role in the thermal control measures and optimization of the structural design of satellites. For achieving real-time thermal stress and thermal deformation analysis of satellite motherboards, this paper proposes a novel Multi-Task Attention UNet (MTA-UNet) neural network which combines the advantages of both Multi-Task Learning (MTL) and U-Net with an attention mechanism. Furthermore, a physics-informed strategy is used in the training process, where partial differential equations (PDEs) are integrated into the loss functions as residual terms. Finally, an uncertainty-based loss balancing approach is applied to weight different loss functions of multiple training tasks. Experimental results show that the proposed MTA-UNet effectively improves the prediction accuracy of multiple physics tasks compared with Single-Task Learning (STL) models. In addition, the physics-informed method brings less error in the prediction of each task, especially on small data sets.
Open AccessPhysics-Informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites
The rapid analysis of thermal stress and deformation plays a pivotal role in the thermal control measures and optimization of the structural design of satellites. For achieving real-time thermal stress and thermal deformation analysis of satellite motherboards, this paper proposes a novel Multi-Task Attention UNet (MTA-UNet) neural network which combines the advantages of both Multi-Task Learning (MTL) and U-Net with an attention mechanism. Furthermore, a physics-informed strategy is used in the training process, where partial differential equations (PDEs) are integrated into the loss functions as residual terms. Finally, an uncertainty-based loss balancing approach is applied to weight different loss functions of multiple training tasks. Experimental results show that the proposed MTA-UNet effectively improves the prediction accuracy of multiple physics tasks compared with Single-Task Learning (STL) models. In addition, the physics-informed method brings less error in the prediction of each task, especially on small data sets.
- Open Access
Heat Source Layout Optimization Using Automatic Deep Learning Surrogate and Multimodal Neighborhood Search Algorithm
In satellite layout design, heat source layout optimization (HSLO) is an effective technique to decrease the maximum temperature and improve the heat management of the whole system. Recently, deep learning surrogate assisted HSLO has been proposed, which learns the mapping from layout to its corresponding temperature field, so as to substitute the simulation during optimization to decrease the computational cost largely. However, it faces two main challenges: 1) the neural network surrogate for the certain task is often manually designed to be complex and requires rich debugging experience, which is challenging for the designers in the engineering field; 2) existing algorithms for HSLO could only obtain a near optimal solution in single optimization and are easily trapped in local optimum. To address the first challenge, considering reducing the total parameter numbers and ensuring the similar accuracy as well as, a neural architecture search (NAS) method combined with Feature Pyramid Network (FPN) framework is developed to realize the purpose of automatically searching for a small deep learning surrogate model for HSLO. To address the second challenge, a multimodal neighborhood search based layout optimization algorithm (MNSLO) is proposed, which could obtain more and better approximate optimal design schemes simultaneously in single optimization. Finally, two typical two-dimensional heat conduction optimization problems are utilized to demonstrate the effectiveness of the proposed method. With the similar accuracy, NAS finds models with 80% fewer parameters, 64% fewer FLOPs and 36% faster inference time than the original FPN. Besides, with the assistance of deep learning surrogate by automatic search, MNSLO could achieve multiple near optimal design schemes simultaneously to provide more design diversities for designers.
Open AccessHeat Source Layout Optimization Using Automatic Deep Learning Surrogate and Multimodal Neighborhood Search Algorithm
In satellite layout design, heat source layout optimization (HSLO) is an effective technique to decrease the maximum temperature and improve the heat management of the whole system. Recently, deep learning surrogate assisted HSLO has been proposed, which learns the mapping from layout to its corresponding temperature field, so as to substitute the simulation during optimization to decrease the computational cost largely. However, it faces two main challenges: 1) the neural network surrogate for the certain task is often manually designed to be complex and requires rich debugging experience, which is challenging for the designers in the engineering field; 2) existing algorithms for HSLO could only obtain a near optimal solution in single optimization and are easily trapped in local optimum. To address the first challenge, considering reducing the total parameter numbers and ensuring the similar accuracy as well as, a neural architecture search (NAS) method combined with Feature Pyramid Network (FPN) framework is developed to realize the purpose of automatically searching for a small deep learning surrogate model for HSLO. To address the second challenge, a multimodal neighborhood search based layout optimization algorithm (MNSLO) is proposed, which could obtain more and better approximate optimal design schemes simultaneously in single optimization. Finally, two typical two-dimensional heat conduction optimization problems are utilized to demonstrate the effectiveness of the proposed method. With the similar accuracy, NAS finds models with 80% fewer parameters, 64% fewer FLOPs and 36% faster inference time than the original FPN. Besides, with the assistance of deep learning surrogate by automatic search, MNSLO could achieve multiple near optimal design schemes simultaneously to provide more design diversities for designers.
- Open Access
RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks
Learning solutions of partial differential equations (PDEs) with Physics-Informed Neural Networks (PINNs) is an attractive alternative approach to traditional solvers due to its flexibility and ease of incorporating observed data. Despite the success of PINNs in accurately solving a wide variety of PDEs, the method still requires improvements in terms of computational efficiency. One possible improvement idea is to optimize the generation of training point sets. Residual-based adaptive sampling and quasi-uniform sampling approaches have been each applied to improve the training effects of PINNs, respectively. To benefit from both methods, we propose the Residual-based Adaptive Node Generation (RANG) approach for efficient training of PINNs, which is based on a variable density nodal distribution method for RBF-FD. The method is also enhanced by a memory mechanism to further improve training stability. We conduct experiments on three linear PDEs and three nonlinear PDEs with various node generation methods, through which the accuracy and efficiency of the proposed method compared to the predominant uniform sampling approach is verified numerically.
Open AccessRANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks
Learning solutions of partial differential equations (PDEs) with Physics-Informed Neural Networks (PINNs) is an attractive alternative approach to traditional solvers due to its flexibility and ease of incorporating observed data. Despite the success of PINNs in accurately solving a wide variety of PDEs, the method still requires improvements in terms of computational efficiency. One possible improvement idea is to optimize the generation of training point sets. Residual-based adaptive sampling and quasi-uniform sampling approaches have been each applied to improve the training effects of PINNs, respectively. To benefit from both methods, we propose the Residual-based Adaptive Node Generation (RANG) approach for efficient training of PINNs, which is based on a variable density nodal distribution method for RBF-FD. The method is also enhanced by a memory mechanism to further improve training stability. We conduct experiments on three linear PDEs and three nonlinear PDEs with various node generation methods, through which the accuracy and efficiency of the proposed method compared to the predominant uniform sampling approach is verified numerically.
- Open Access
FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack
Physical adversarial attacks in object detection have attracted increasing attention. However, most previous works focus on hiding the objects from the detector by generating an individual adversarial patch, which only covers the planar part of the vehicle's surface and fails to attack the detector in physical scenarios for multi-view, long-distance and partially occluded objects. To bridge the gap between digital attacks and physical attacks, we exploit the full 3D vehicle surface to propose a robust Full-coverage Camouflage Attack (FCA) to fool detectors. Specifically, we first try rendering the nonplanar camouflage texture over the full vehicle surface. To mimic the real-world environment conditions, we then introduce a transformation function to transfer the rendered camouflaged vehicle into a photo realistic scenario. Finally, we design an efficient loss function to optimize the camouflage texture. Experiments show that the full-coverage camouflage attack can not only outperform state-of-the-art methods under various test cases but also generalize to different environments, vehicles, and object detectors. The code of FCA will be available at: https://idrl-lab.github.io/Full-coverage-camouflage-adversarial-attack/.
Open AccessFCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack
Physical adversarial attacks in object detection have attracted increasing attention. However, most previous works focus on hiding the objects from the detector by generating an individual adversarial patch, which only covers the planar part of the vehicle's surface and fails to attack the detector in physical scenarios for multi-view, long-distance and partially occluded objects. To bridge the gap between digital attacks and physical attacks, we exploit the full 3D vehicle surface to propose a robust Full-coverage Camouflage Attack (FCA) to fool detectors. Specifically, we first try rendering the nonplanar camouflage texture over the full vehicle surface. To mimic the real-world environment conditions, we then introduce a transformation function to transfer the rendered camouflaged vehicle into a photo realistic scenario. Finally, we design an efficient loss function to optimize the camouflage texture. Experiments show that the full-coverage camouflage attack can not only outperform state-of-the-art methods under various test cases but also generalize to different environments, vehicles, and object detectors. The code of FCA will be available at: https://idrl-lab.github.io/Full-coverage-camouflage-adversarial-attack/.
- Open Access
- 31 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 140038-140053
A Deep Learning-Based Method for Heat Source Layout Inverse Design
Heat source layout design is an effective technique to enhance the thermal performance in the whole system, which has become a vital part in many engineering fields, e.g. satellite layout design and integrated circuit design. Traditionally, the optimal design is obtained by searching the design space with the optimization technique which repeatedly runs the thermal simulation to compare the performance of each scheme. Due to the extremely large computational burden with this method, the optimization is greatly limited. To overcome the challenge, heat source layout inverse design (HSLID) is proposed in this paper to directly generate the layout scheme with the given thermal performance requirement. A novel method for heat source layout inverse design, denoted as SAR-HSLID, is proposed based on the recently deep learning technique, Show Attend and Read (SAR) model. Firstly, regarding the mapping from the required temperature field to layout scheme as an image-to-location task, this paper introduces SAR model, which is good at sequence predicting, to generate the layout scheme. The trained SAR is capable of learning the underlying physics of the design problem, thus can efficiently predict the design under given requirement without any physical simulation. Secondly, to ensure that the designed heat source layout exactly satisfies the input temperature field requirement, based on the layout predicted by SAR, we further utilize a simple but efficient optimization process to conduct few post-processing. Finally, a heat source layout inverse design task in a typical two-dimensional heat conduction problem is investigated to demonstrate the feasibility and effectiveness of the proposed method.
- 31 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 140038-140053
Open AccessA Deep Learning-Based Method for Heat Source Layout Inverse Design
Heat source layout design is an effective technique to enhance the thermal performance in the whole system, which has become a vital part in many engineering fields, e.g. satellite layout design and integrated circuit design. Traditionally, the optimal design is obtained by searching the design space with the optimization technique which repeatedly runs the thermal simulation to compare the performance of each scheme. Due to the extremely large computational burden with this method, the optimization is greatly limited. To overcome the challenge, heat source layout inverse design (HSLID) is proposed in this paper to directly generate the layout scheme with the given thermal performance requirement. A novel method for heat source layout inverse design, denoted as SAR-HSLID, is proposed based on the recently deep learning technique, Show Attend and Read (SAR) model. Firstly, regarding the mapping from the required temperature field to layout scheme as an image-to-location task, this paper introduces SAR model, which is good at sequence predicting, to generate the layout scheme. The trained SAR is capable of learning the underlying physics of the design problem, thus can efficiently predict the design under given requirement without any physical simulation. Secondly, to ensure that the designed heat source layout exactly satisfies the input temperature field requirement, based on the layout predicted by SAR, we further utilize a simple but efficient optimization process to conduct few post-processing. Finally, a heat source layout inverse design task in a typical two-dimensional heat conduction problem is investigated to demonstrate the feasibility and effectiveness of the proposed method.
- 27 February 2020
- Published by Springer Nature in Journal of Global Optimization
- Vol. 78 (1) , 69-89
Global complexity analysis of inexact successive quadratic approximation methods for regularized optimization under mild assumptions
- 27 February 2020
- Published by Springer Nature in Journal of Global Optimization
- Vol. 78 (1) , 69-89
Global complexity analysis of inexact successive quadratic approximation methods for regularized optimization under mild assumptions
- Open Access
- 22 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 126515-126529
Bregman Proximal Gradient Algorithm With Extrapolation for a Class of Nonconvex Nonsmooth Minimization Problems
In this paper, we consider an accelerated method for solving nonconvex and nonsmooth minimization problems. We propose a Bregman Proximal Gradient algorithm with extrapolation(BPGe). This algorithm extends and accelerates the Bregman Proximal Gradient algorithm (BPG), which circumvents the restrictive global Lipschitz gradient continuity assumption needed in Proximal Gradient algorithms (PG). The BPGe algorithm has a greater generality than the recently introduced Proximal Gradient algorithm with extrapolation (PGe) and, in addition, due to the extrapolation step, BPGe converges faster than the BPG algorithm. Analyzing the convergence, we prove that any limit point of the sequence generated by BPGe is a stationary point of the problem by choosing the parameters properly. Besides, assuming Kurdyka#ojasiewicz property, we prove that all the sequences generated by BPGe converge to a stationary point. Finally, to illustrate the potential of the new method BPGe, we apply it to two important practical problems that arise in many fundamental applications (and that not satisfy global Lipschitz gradient continuity assumption): Poisson linear inverse problems and quadratic inverse problems. In the tests the accelerated BPGe algorithm shows faster convergence results, giving an interesting new algorithm.
- 22 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 126515-126529
Open AccessBregman Proximal Gradient Algorithm With Extrapolation for a Class of Nonconvex Nonsmooth Minimization Problems
In this paper, we consider an accelerated method for solving nonconvex and nonsmooth minimization problems. We propose a Bregman Proximal Gradient algorithm with extrapolation(BPGe). This algorithm extends and accelerates the Bregman Proximal Gradient algorithm (BPG), which circumvents the restrictive global Lipschitz gradient continuity assumption needed in Proximal Gradient algorithms (PG). The BPGe algorithm has a greater generality than the recently introduced Proximal Gradient algorithm with extrapolation (PGe) and, in addition, due to the extrapolation step, BPGe converges faster than the BPG algorithm. Analyzing the convergence, we prove that any limit point of the sequence generated by BPGe is a stationary point of the problem by choosing the parameters properly. Besides, assuming Kurdyka#ojasiewicz property, we prove that all the sequences generated by BPGe converge to a stationary point. Finally, to illustrate the potential of the new method BPGe, we apply it to two important practical problems that arise in many fundamental applications (and that not satisfy global Lipschitz gradient continuity assumption): Poisson linear inverse problems and quadratic inverse problems. In the tests the accelerated BPGe algorithm shows faster convergence results, giving an interesting new algorithm.