1 code implementation • 25 Nov 2023 • Zhiqiang Gong, Xian Zhou, Wen Yao, Xiaohu Zheng, Ping Zhong
To address this limitation, this study rethinks hyperspectral intrinsic image decomposition for classification tasks by introducing deep feature embedding.
no code implementations • 3 Nov 2023 • Donghua Wang, Wen Yao, Tingsong Jiang, Xiaoqian Chen
In this paper, we propose a novel universal perturbation-based secret key-controlled data-hiding method, realizing data hiding with a single universal perturbation and data decoding with the secret key-controlled decoder.
1 code implementation • 1 Nov 2023 • Jiakai Wang, Donghua Wang, Jin Hu, Siyang Wu, Tingsong Jiang, Wen Yao, Aishan Liu, Xianglong Liu
However, current research on physical adversarial examples (PAEs) lacks a comprehensive understanding of their unique characteristics, leading to limited significance and understanding.
no code implementations • 28 Oct 2023 • Zhiqiang Gong, Xian Zhou, Wen Yao
Due to the powerful ability in capturing the global information, Transformer has become an alternative architecture of CNNs for hyperspectral image classification.
no code implementations • 28 Oct 2023 • Zhiqiang Gong, Xian Zhou, Wen Yao
Convolutional neural networks (CNNs) have been demonstrated their powerful ability to extract discriminative features for hyperspectral image classification.
1 code implementation • ICCV 2023 • Donghua Wang, Wen Yao, Tingsong Jiang, Chao Li, Xiaoqian Chen
In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object.
no code implementations • 13 Jul 2023 • Jialiang Sun, Wen Yao, Tingsong Jiang, Xiaoqian Chen
To bridge the gap between AutoML and semantic adversarial attacks, we propose a novel method called multi-objective evolutionary search of variable-length composite semantic perturbations (MES-VCSP).
no code implementations • 12 May 2023 • Jialiang Sun, Wen Yao, Tingsong Jiang, Xiaoqian Chen
Finally, we propose a multi-fidelity online surrogate during optimization to further decrease the search cost.
no code implementations • 21 Apr 2023 • Chengyin Hu, Weiwen Shi, Tingsong Jiang, Wen Yao, Ling Tian, Xiaoqian Chen
Infrared imaging systems have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern.
no code implementations • 20 Apr 2023 • Donghua Wang, Wen Yao, Tingsong Jiang, Weien Zhou, Lang Lin, Xiaoqian Chen
Then, we extract the copyright information from the encoded copyrighted image with the devised copyright decoder.
no code implementations • 14 Apr 2023 • Yanfang Lyu, Xiaoyu Zhao, Zhiqiang Gong, Xiao Kang, Wen Yao
Therefore, this work proposes a novel multi-fidelity learning method based on the Fourier Neural Operator by jointing abundant low-fidelity data and limited high-fidelity data under transfer learning paradigm.
1 code implementation • 23 Feb 2023 • Yunyang Zhang, Zhiqiang Gong, Xiaoyu Zhao, Wen Yao
Recovering a globally accurate complex physics field from limited sensor is critical to the measurement and control in the aerospace engineering.
1 code implementation • 20 Feb 2023 • Xiaoyu Zhao, Xiaoqian Chen, Zhiqiang Gong, Weien Zhou, Wen Yao, Yunyang Zhang
The MLP embedding is propitious to more sparse input, while the others benefit from spatial information preservation and perform better with the increase of observation data.
no code implementations • 17 Jan 2023 • Yunyang Zhang, Zhiqiang Gong, Weien Zhou, Xiaoyu Zhao, Xiaohu Zheng, Wen Yao
Then, a self-supervised learning method for training the physics-driven deep multi-fidelity model (PD-DMFM) is proposed, which fully utilizes the physics characteristics of the engineering systems and reduces the dependence on large amounts of labeled low-fidelity data in the training process.
no code implementations • 6 Dec 2022 • Zixue Xiang, Wei Peng, Wen Yao
We introduce GNNs into physics-informed learning to better handle irregular domains with unstructured meshes.
1 code implementation • 19 Oct 2022 • Wei Peng, Wen Yao, Weien Zhou, Xiaoya Zhang, Weijie Yao
Physics-informed neural networks (PINNs) have been proposed to solve two main classes of problems: data-driven solutions and data-driven discovery of partial differential equations.
no code implementations • 17 Oct 2022 • Jialiang Sun, Tingsong Jiang, Wen Yao, Donghua Wang, Xiaoqian Chen
In the first stage, we optimize the global texture to minimize the discrepancy between the rendered object and the scene images, making human eyes difficult to distinguish.
no code implementations • 28 Sep 2022 • Donghua Wang, Wen Yao, Tingsong Jiang, Guijian Tang, Xiaoqian Chen
Then, we discuss the existing physical attacks and focus on the technique for improving the robustness of physical attacks under complex physical environmental conditions.
no code implementations • 1 Sep 2022 • Zeyu Cao, Wen Yao, Wei Peng, Xiaoya Zhang, Kairui Bao
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.
no code implementations • 15 Aug 2022 • Jialiang Sun, Wen Yao, Tingsong Jiang, Xiaoqian Chen
Therefore, we propose a multi-objective memetic algorithm for auto adversarial attack optimization design, which realizes the automatical search for the near-optimal adversarial attack towards defensed models.
no code implementations • 15 Jun 2022 • Xu Liu, Wen Yao, Xiaohu Zheng, Yingchun Xu
To overcome the respective defects of UGF and BN, a novel reliability analysis method called UGF-BN is proposed for the complex MSS.
no code implementations • 16 May 2022 • Jialiang Sun, Xiaohu Zheng, Wen Yao, Xiaoya Zhang, Weien Zhou, Xiaoqian Chen
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.
no code implementations • 14 May 2022 • Xu Liu, Wen Yao, Wei Peng, Weien Zhou
Besides, for inverse PDE problems, problem parameters considered as new output layer weights are unified in a framework with forward PDE problems.
1 code implementation • 2 May 2022 • Wei Peng, Weien Zhou, Xiaoya Zhang, Wen Yao, Zheliang Liu
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.
no code implementations • 4 Apr 2022 • Xiaohu Zheng, Wen Yao, Xiaoqian Chen
This Part II proposes a novel method for BN reliability modeling and analysis to apply the compression idea to the complex multistate dependent system.
1 code implementation • 29 Mar 2022 • Xiaohu Zheng, Wen Yao, Yunyang Zhang, Xiaoya Zhang
To alleviate this problem, this paper proposes a consistency regularization-based deep polynomial chaos neural network (Deep PCNN) method, including the low-order adaptive PCE model (the auxiliary model) and the high-order polynomial chaos neural network (the main model).
no code implementations • 15 Mar 2022 • Kairui Bao, Wen Yao, Xiaoya Zhang, Wei Peng, Yu Li
Second, a physics-driven CNN surrogate with partial differential equation (PDE) residuals as a loss function is utilized for fast meshing (meshing surrogate); then, we present a data-driven surrogate model based on the multi-level reduced-order method, aiming to learn solutions of temperature field in the above regular computational plane (thermal surrogate).
no code implementations • 10 Mar 2022 • Yunyang Zhang, Zhiqiang Gong, Xiaohu Zheng, Xiaoyu Zhao, Wen Yao
However, the wrong pseudo labeling information generated by cross supervision would confuse the training process and negatively affect the effectiveness of the segmentation model.
1 code implementation • 8 Mar 2022 • Xiaoyu Zhao, Xiaoqian Chen, Zhiqiang Gong, Wen Yao, Yunyang Zhang, Xiaohu Zheng
This paper proposes a contrastive enhancement approach using latent prototypes to leverage latent classes and raise the utilization of similarity information between prototype and query features.
no code implementations • 7 Mar 2022 • Jialiang Sun, Wen Yao, Tingsong Jiang, Chao Li, Xiaoqian Chen
To alleviate these problems, in this paper, we first propose a novel platform called auto adversarial attack and defense ($A^{3}D$), which can help search for robust neural network architectures and efficient adversarial attacks.
1 code implementation • 14 Feb 2022 • Xiaohu Zheng, Wen Yao, Zhiqiang Gong, Yunyang Zhang, Xiaoyu Zhao, Tingsong Jiang
However, a lot of labeled data is needed to train CNN, and the common CNN can not quantify the aleatoric uncertainty caused by data noise.
no code implementations • 14 Feb 2022 • Xiaohu Zheng, Wen Yao, Zhiqiang Gong, Yunyang Zhang, Xiaoya Zhang
To solve the above problem, this paper proposes an unsupervised method, i. e., the physics-informed deep Monte Carlo quantile regression method, for reconstructing temperature field and quantifying the aleatoric uncertainty caused by data noise.
no code implementations • 26 Jan 2022 • Xingwen Peng, Xingchen Li, Zhiqiang Gong, Xiaoyu Zhao, Wen Yao
To solve the problem, this work proposes a novel deep learning method based on patchwise training to reconstruct the temperature field of electronic equipment accurately from limited observation.
1 code implementation • 18 Jan 2022 • Xu Liu, Wei Peng, Zhiqiang Gong, Weien Zhou, Wen Yao
In this work, we develop a physics-informed neural network-based temperature field inversion (PINN-TFI) method to solve the TFI-HSS task and a coefficient matrix condition number based position selection of observations (CMCN-PSO) method to select optima positions of noise observations.
1 code implementation • 26 Sep 2021 • Xiaoyu Zhao, Zhiqiang Gong, Yunyang Zhang, Wen Yao, Xiaoqian Chen
As the construction of data pairs in most engineering problems is time-consuming, data acquisition is becoming the predictive capability bottleneck of most deep surrogate models, which also exists in surrogate for thermal analysis and design.
1 code implementation • 15 Sep 2021 • Donghua Wang, Tingsong Jiang, Jialiang Sun, Weien Zhou, Xiaoya Zhang, Zhiqiang Gong, Wen Yao, Xiaoqian Chen
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.
2 code implementations • 17 Aug 2021 • Xiaoqian Chen, Zhiqiang Gong, Xiaoyu Zhao, Weien Zhou, Wen Yao
To overcome this problem, this work develops a machine learning modelling benchmark for TFR-HSS task.
no code implementations • 23 Jul 2021 • Xu Liu, Xiaoya Zhang, Wei Peng, Weien Zhou, Wen Yao
Inspired by this idea, we propose the new Reptile initialization to sample more tasks from the parameterized PDEs and adapt the penalty term of the loss.
1 code implementation • 22 Jul 2021 • Wen Yao, Xiaohu Zheng, Jun Zhang, Ning Wang, Guijian Tang
Based on the adaptive aPC, a semi-supervised deep adaptive arbitrary polynomial chaos expansion (Deep aPCE) method is proposed to reduce the training data cost and improve the surrogate model accuracy.
no code implementations • 15 Jul 2021 • Yufeng Xia, Jun Zhang, Zhiqiang Gong, Tingsong Jiang, Wen Yao
Deep Ensemble is widely considered the state-of-the-art method which can estimate the uncertainty with higher quality, but it is very expensive to train and test.
1 code implementation • 9 Jul 2021 • Wei Peng, Jun Zhang, Weien Zhou, Xiaoyu Zhao, Wen Yao, Xiaoqian Chen
Physics Informed Neural Network (PINN) is a scientific computing framework used to solve both forward and inverse problems modeled by Partial Differential Equations (PDEs).
1 code implementation • 22 Jun 2021 • Zhiqiang Gong, Weien Zhou, Jun Zhang, Wei Peng, Wen Yao
To solve this problem, this work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems (TFR-HSS), which can better reconstruct the temperature field with limited monitoring points unsupervisedly.
1 code implementation • 20 Mar 2021 • Xianqi Chen, Xiaoyu Zhao, Zhiqiang Gong, Jun Zhang, Weien Zhou, Xiaoqian Chen, Wen Yao
Thermal issue is of great importance during layout design of heat source components in systems engineering, especially for high functional-density products.
1 code implementation • 17 Apr 2020 • Wei Peng, Weien Zhou, Jun Zhang, Wen Yao
Physics-Informed Neural Networks (PINNs) can be regarded as general-purpose PDE solvers, but it might be slow to train PINNs on particular problems, and there is no theoretical guarantee of corresponding error bounds.
no code implementations • 10 Mar 2020 • Biao Gao, Anran Xu, Yancheng Pan, Xijun Zhao, Wen Yao, Huijing Zhao
We propose a method for off-road drivable area extraction using 3D LiDAR data with the goal of autonomous driving application.
no code implementations • 3 Sep 2018 • Jilin Mei, Biao Gao, Donghao Xu, Wen Yao, Xijun Zhao, Huijing Zhao
This work studies the semantic segmentation of 3D LiDAR data in dynamic scenes for autonomous driving applications.
Robotics