Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the rea...Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the real world,which makes the existing approaches perform poorly for recognition tasks in different scenes.In this paper,we propose a domain generaliza-tion framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments.Specifically,we propose an end-to-end denoising based domain-invariant radar emitter recognition network(DDIRNet)consisting of a denoising model and a domain invariant representation learning model(IRLM),which mutually benefit from each other.For the signal denoising model,a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model.For the domain invariant representation learning model,contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distri-bution.Moreover,we design a data augmentation method that improves the diversity of signal data for training.Extensive experiments on classification have shown that DDIRNet achieves up to 6.4%improvement compared with the state-of-the-art radar emitter recognition methods.The proposed method pro-vides a promising direction to solve the radar emitter signal recognition problem.展开更多
In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when fa...In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when faced with testing scenarios from unknown domains.To address this problem,this paper proposes a novel semi-supervised approach for cardiac magnetic resonance image segmentation,aiming to enhance predictive capabilities and domain generalization(DG).This paper establishes an MT-like model utilizing pseudo-labeling and consistency regularization from semi-supervised learning,and integrates uncertainty estimation to improve the accuracy of pseudo-labels.Additionally,to tackle the challenge of domain generalization,a data manipulation strategy is introduced,extracting spatial and content-related information from images across different domains,enriching the dataset with a multi-domain perspective.This papers method is meticulously evaluated on the publicly available cardiac magnetic resonance imaging dataset M&Ms,validating its effectiveness.Comparative analyses against various methods highlight the out-standing performance of this papers approach,demonstrating its capability to segment cardiac magnetic resonance images in previously unseen domains even with limited annotated data.展开更多
Learning domain-invariant feature representations is critical to alleviate the distribution differences between training and testing domains.The existing mainstream domain generalization approaches primarily pursue to...Learning domain-invariant feature representations is critical to alleviate the distribution differences between training and testing domains.The existing mainstream domain generalization approaches primarily pursue to align the across-domain distributions to extract the transferable feature representations.However,these representations may be insufficient and unstable.Moreover,these networks may also undergo catastrophic forgetting because the previous learned knowledge is replaced by the new learned knowledge.To cope with these issues,we propose a novel causality-based contrastive incremental learning model for domain generalization,which mainly includes three components:(1)intra-domain causal factorization,(2)inter-domain Mahalanobis similarity metric,and(3)contrastive knowledge distillation.The model extracts intra and inter domain-invariant knowledge to improve model generalization.Specifically,we first introduce a causal factorization to extract intra-domain invariant knowledge.Then,we design a Mahalanobis similarity metric to extract common inter-domain invariant knowledge.Finally,we propose a contrastive knowledge distillation with exponential moving average to distill model parameters in a smooth way to preserve the previous learned knowledge and mitigate model forgetting.Extensive experiments on several domain generalization benchmarks prove that our model achieves the state-of-the-art results,which sufficiently show the effectiveness of our model.展开更多
Emotion recognition from physiological signals(ERPS)has drawn tremendous attention and can be potentially applied to numerous fields.Since physiological signals are nonstationary time series with high sampling frequen...Emotion recognition from physiological signals(ERPS)has drawn tremendous attention and can be potentially applied to numerous fields.Since physiological signals are nonstationary time series with high sampling frequency,it is challenging to directly extract features from them.Additionally,there are 2 major challenges in ERPS:(a)how to adequately capture the correlations between physiological signals at different times and between different types of physiological signals and(b)how to effectively minimize the negative effect caused by temporal covariate shift(TCS).To tackle these problems,we propose a domain generalization and residual network-based approach for emotion recognition from physiological signals(DGR-ERPS).We first pre-extract time-and frequency-domain features from the original time series to compose a new time series.Then,in order to fully extract the correlation information of different physiological signals,these time series are converted into 3D image data to serve as input for a residual-based feature encoder(RBFE).In addition,we introduce a domain generalization-based technique to mitigate the issue posed by TCS.We have conducted extensive experiments on 2 real-world datasets,and the results indicate that our DGR-ERPS achieves superior performance under both TCS and non-TCS scenarios.展开更多
In this paper,we first obtain a unified integral representation on the analytic varieties of the general bounded domain in Stein manifolds(the two types bounded domains in[3]are regarded as its special cases).Secondly...In this paper,we first obtain a unified integral representation on the analytic varieties of the general bounded domain in Stein manifolds(the two types bounded domains in[3]are regarded as its special cases).Secondly we get the integral formulas of the solution of∂-equation.And we use a new and unique method to give a uniform estimate of the solution of∂-equation,which is different from Henkin's method.展开更多
Intelligent machinery fault diagnosis methods have been popularly and successfully developed in the past decades,and the vibration acceleration data collected by contact accelerometers have been widely investigated.In...Intelligent machinery fault diagnosis methods have been popularly and successfully developed in the past decades,and the vibration acceleration data collected by contact accelerometers have been widely investigated.In many industrial scenarios,contactless sensors are more preferred.The event camera is an emerging bio-inspired technology for vision sensing,which asynchronously records per-pixel brightness change polarity with high temporal resolution and low latency.It offers a promising tool for contactless machine vibration sensing and fault diagnosis.However,the dynamic vision-based methods suffer from variations of practical factors such as camera position,machine operating condition,etc.Furthermore,as a new sensing technology,the labeled dynamic vision data are limited,which generally cannot cover a wide range of machine fault modes.Aiming at these challenges,a novel dynamic vision-based machinery fault diagnosis method is proposed in this paper.It is motivated to explore the abundant vibration acceleration data for enhancing the dynamic vision-based model performance.A crossmodality feature alignment method is thus proposed with deep adversarial neural networks to achieve fault diagnosis knowledge transfer.An event erasing method is further proposed for improving model robustness against variations.The proposed method can effectively identify unseen fault mode with dynamic vision data.Experiments on two rotating machine monitoring datasets are carried out for validations,and the results suggest the proposed method is promising for generalized contactless machinery fault diagnosis.展开更多
As failure data is usually scarce in practice upon preventive maintenance strategy in prognostics and health management(PHM)domain,transfer learning provides a fundamental solution to enhance generalization of datadri...As failure data is usually scarce in practice upon preventive maintenance strategy in prognostics and health management(PHM)domain,transfer learning provides a fundamental solution to enhance generalization of datadriven methods.In this paper,we briefly discuss general idea and advances of various transfer learning techniques in PHM domain,including domain adaptation,domain generalization,federated learning,and knowledge-driven transfer learning.Based on the observations from state of the art,we provide extensive discussions on possible challenges and opportunities of transfer learning in PHM domain to direct future development.展开更多
In response to real-world scenarios,the domain generalization(DG)problem has spurred considerable research in person re-identification(ReID).This challenge arises when the target domain,which is significantly differen...In response to real-world scenarios,the domain generalization(DG)problem has spurred considerable research in person re-identification(ReID).This challenge arises when the target domain,which is significantly different from the source domains,remains unknown.However,the performance of current DG ReID relies heavily on labor-intensive source domain annotations.Considering the potential of unlabeled data,we investigate unsupervised domain generalization(UDG)in ReID.Our goal is to create a model that can generalize from unlabeled source domains to semantically retrieve images in an unseen target domain.To address this,we propose a new approach that trains a domain-agnostic expert(DaE)for unsupervised domain-generalizable person ReID.This involves independently training multiple experts to account for label space inconsistencies between source domains.At the same time,the DaE captures domain-generalizable information for testing.Our experiments demonstrate the effectiveness of this method for learning generalizable features under the UDG setting.The results demonstrate the superiority of our method over state-of-the-art techniques.We will make our code and models available for public use.展开更多
We study the initial-boundary value problem of the Navier-Stokes equations for incompressible fluids in a general domain in R^n with compact and smooth boundary, subject to the kinematic and vorticity boundary conditi...We study the initial-boundary value problem of the Navier-Stokes equations for incompressible fluids in a general domain in R^n with compact and smooth boundary, subject to the kinematic and vorticity boundary conditions on the non-flat boundary. We observe that, under the nonhomogeneous boundary conditions, the pressure p can be still recovered by solving the Neumann problem for the Poisson equation. Then we establish the well-posedness of the unsteady Stokes equations and employ the solution to reduce our initial-boundary value problem into an initial-boundary value problem with absolute boundary conditions. Based on this, we first establish the well-posedness for an appropriate local linearized problem with the absolute boundary conditions and the initial condition （without the incompressibility condition）, which establishes a velocity mapping. Then we develop apriori estimates for the velocity mapping, especially involving the Sobolev norm for the time-derivative of the mapping to deal with the complicated boundary conditions, which leads to the existence of the fixed point of the mapping and the existence of solutions to our initial-boundary value problem. Finally, we establish that, when the viscosity coefficient tends zero, the strong solutions of the initial-boundary value problem in R^n（n ≥ 3） with nonhomogeneous vorticity boundary condition converge in L^2 to the corresponding Euler equations satisfying the kinematic condition.展开更多
Domain generalizable person re-identification(reid)is a challenging task in computer vision,which aims to apply a trained reid model to unseen domains.Prior works either combine the data in all the training domains to...Domain generalizable person re-identification(reid)is a challenging task in computer vision,which aims to apply a trained reid model to unseen domains.Prior works either combine the data in all the training domains to capture domain-invariant features,or adopt a mixture of experts to investigate domain-specific information.In this work,we argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of reid models.To this end,we design a novel framework,which we name two-stream adaptive learning(TAL),to simultaneously model these two kinds of information.Specifically,a domain-specific stream is proposed to capture the training domain statistics with batch normalization(BN)parameters,whereas an adaptive matching layer is designed to dynamically aggregate domain-level information.In the meantime,we design an adaptive BN layer in the domain-invariant stream to approximate the statistic of unseen domains,such that our model is capable of handling various novel scenes.These two streams work adaptively and collaboratively to learn generalizable reid features.As validated by extensive experiments,our framework can be applied to both single-source and multi-source domain generalization tasks,where the results show that our framework notably outperforms the state-of-the-art methods.展开更多
Generalizable pedestrian attribute recognition(PAR)aims to learn a robust PAR model that can be directly adapted to unknown distributions under varying illumination,different viewpoints and occlusions,which is an esse...Generalizable pedestrian attribute recognition(PAR)aims to learn a robust PAR model that can be directly adapted to unknown distributions under varying illumination,different viewpoints and occlusions,which is an essential problem for real-world applications,such as video surveillance and fashion search.In practice,when a trained PAR model is deployed to real-world scenarios,the unseen target samples are fed into the model continuously in an online manner.Therefore,this paper proposes an efficient and flexible method,named AdaGPAR,for generalizable PAR(GPAR)via test-time adaptation(TTA),where we adapt the trained model through exploiting the unlabeled target samples online during the test phase.As far as we know,it is the first work that solves the GPAR from the perspective of TTA.In particular,the proposed AdaGPAR memorizes the reliable target sample pairs(features and pseudo-labels)as prototypes gradually in the test phase.Then,it makes predictions with a non-parametric classifier by calculating the similarity between a target instance and the prototypes.However,since PAR is a task of multi-label classification,only using the same holistic feature of one pedestrian image as the prototypes of multiple attributes is not optimal.Therefore,an attribute localization branch is introduced to extract the attribute-specific features,where two kinds of memory banks are further constructed to cache the global and attribute-specific features simultaneously.In summary,the AdaGPAR is training-free in the test phase and predicts multiple pedestrian attributes of the target samples in an online manner.This makes the AdaGPAR time efficient and generalizable for real-world applications.Extensive experiments have been performed on the UPAR benchmark to compare the proposed method with multiple baselines.The superior performance demonstrates the effectiveness of the proposed AdaGPAR that improves the generalizability of a PAR model via TTA.展开更多
Gear pitting fault is a common issue in gear systems,affecting transmission efficiency and potentially leading to severe equipment shutdowns.Effective diagnosis enhances reliability,reduces maintenance costs,and exten...Gear pitting fault is a common issue in gear systems,affecting transmission efficiency and potentially leading to severe equipment shutdowns.Effective diagnosis enhances reliability,reduces maintenance costs,and extends equipment lifespan.However,existing deep learning based methods often neglect the inherent structure of temporal vibration signals and fail to address domain variations,resulting in poor generalization and performance.To overcome these limitations,we propose a novel approach based on domain-independent features.Vibration signals are mapped to time-frequency representations via short-time Fourier transform,and dependencies between different frequencies are effectively captured using a Transformer encoder.The proposed method incorporates a feature decoupling structure that combines singular value decomposition and Pearson correlation coefficient to extract low-rank approximations of domain-related and pitting-related features,while quantifying their correlation.This approach mitigates feature degradation in constructing domain-independent features.Additionally,the weighted LinSoftmax function is introduced as a replacement for the traditional Softmax,leading to a more stable optimization target and improved model accuracy,with a distance-based penalty weight focusing on significant prediction errors.Experiments on the 2023 PHM Data Challenge dataset demonstrate the effectiveness of the proposed method,achieving a mean absolute error of 0.11,an accuracy of 92.32%,and a fault tolerance accuracy of 98.02%.展开更多
Implementing Structural Health Monitoring(SHM)systems with extensive sensing layouts on all civil structures is obviously expensive and unfeasible.Thus,estimating the state(condition)of dissimilar civil structures bas...Implementing Structural Health Monitoring(SHM)systems with extensive sensing layouts on all civil structures is obviously expensive and unfeasible.Thus,estimating the state(condition)of dissimilar civil structures based on the information collected from other structures is regarded as a useful and essential way.For this purpose,Structural State Translation(SST)has been recently proposed to predict the response data of civil structures based on the information acquired from a dissimilar structure.This study uses the SST methodology to translate the state of one bridge(Bridge#1)to a new state based on the knowledge acquired from a structurally dissimilar bridge(Bridge#2).Specifically,the Domain-Generalized Cycle-Generative(DGCG)model is trained in the Domain Generalization learning approach on two distinct data domains obtained from Bridge#1;the bridges have two different conditions:State-H and State-D.Then,the model is used to generalize and transfer the knowledge on Bridge#1 to Bridge#2.In doing so,DGCG translates the state of Bridge#2 to the state that the model has learned after being trained.In one scenario,Bridge#2’s State-H is translated to State-D;in another scenario,Bridge#2’s State-D is translated to State-H.The translated bridge states are then compared with the real ones via modal identifiers and mean magnitude-squared coherence(MMSC),showing that the translated states are remarkably similar to the real ones.For instance,the modes of the translated and real bridge states are similar,with the maximum frequency difference of 1.12%and the minimum correlation of 0.923 in Modal Assurance Criterion values,as well as the minimum of 0.947 in Average MMSC values.In conclusion,this study demonstrates that SST is a promising methodology for research with data scarcity and population-based structural health monitoring(PBSHM).In addition,a critical discussion about the methodology adopted in this study is also offered to address some related concerns.展开更多
In this paper, we consider the viscous incompressible magnetohydrodynamic （MHD） system with a new boundary condition for a general smooth domain in R^3. We obtain the well-posedness of the system and the vanishing v...In this paper, we consider the viscous incompressible magnetohydrodynamic （MHD） system with a new boundary condition for a general smooth domain in R^3. We obtain the well-posedness of the system and the vanishing viscosity limit result.展开更多
基金supported by the National Natural Science Foundation of China(62101575)the Research Project of NUDT(ZK22-57)the Self-directed Project of State Key Laboratory of High Performance Computing(202101-16).
文摘Automatically recognizing radar emitters from com-plex electromagnetic environments is important but non-trivial.Moreover,the changing electromagnetic environment results in inconsistent signal distribution in the real world,which makes the existing approaches perform poorly for recognition tasks in different scenes.In this paper,we propose a domain generaliza-tion framework is proposed to improve the adaptability of radar emitter signal recognition in changing environments.Specifically,we propose an end-to-end denoising based domain-invariant radar emitter recognition network(DDIRNet)consisting of a denoising model and a domain invariant representation learning model(IRLM),which mutually benefit from each other.For the signal denoising model,a loss function is proposed to match the feature of the radar signals and guarantee the effectiveness of the model.For the domain invariant representation learning model,contrastive learning is introduced to learn the cross-domain feature by aligning the source and unseen domain distri-bution.Moreover,we design a data augmentation method that improves the diversity of signal data for training.Extensive experiments on classification have shown that DDIRNet achieves up to 6.4%improvement compared with the state-of-the-art radar emitter recognition methods.The proposed method pro-vides a promising direction to solve the radar emitter signal recognition problem.
基金Supported by the National Natural Science Foundation of China(No.62001313)the Key Project of Liaoning Provincial Department of Science and Technology(No.2021JH2/10300134,2022JH1/10500004)。
文摘In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when faced with testing scenarios from unknown domains.To address this problem,this paper proposes a novel semi-supervised approach for cardiac magnetic resonance image segmentation,aiming to enhance predictive capabilities and domain generalization(DG).This paper establishes an MT-like model utilizing pseudo-labeling and consistency regularization from semi-supervised learning,and integrates uncertainty estimation to improve the accuracy of pseudo-labels.Additionally,to tackle the challenge of domain generalization,a data manipulation strategy is introduced,extracting spatial and content-related information from images across different domains,enriching the dataset with a multi-domain perspective.This papers method is meticulously evaluated on the publicly available cardiac magnetic resonance imaging dataset M&Ms,validating its effectiveness.Comparative analyses against various methods highlight the out-standing performance of this papers approach,demonstrating its capability to segment cardiac magnetic resonance images in previously unseen domains even with limited annotated data.
基金supported by the Pre-research Project on Civil Aerospace Technologies of China National Space Administration(No.D010301).
文摘Learning domain-invariant feature representations is critical to alleviate the distribution differences between training and testing domains.The existing mainstream domain generalization approaches primarily pursue to align the across-domain distributions to extract the transferable feature representations.However,these representations may be insufficient and unstable.Moreover,these networks may also undergo catastrophic forgetting because the previous learned knowledge is replaced by the new learned knowledge.To cope with these issues,we propose a novel causality-based contrastive incremental learning model for domain generalization,which mainly includes three components:(1)intra-domain causal factorization,(2)inter-domain Mahalanobis similarity metric,and(3)contrastive knowledge distillation.The model extracts intra and inter domain-invariant knowledge to improve model generalization.Specifically,we first introduce a causal factorization to extract intra-domain invariant knowledge.Then,we design a Mahalanobis similarity metric to extract common inter-domain invariant knowledge.Finally,we propose a contrastive knowledge distillation with exponential moving average to distill model parameters in a smooth way to preserve the previous learned knowledge and mitigate model forgetting.Extensive experiments on several domain generalization benchmarks prove that our model achieves the state-of-the-art results,which sufficiently show the effectiveness of our model.
基金supported in part by the National Natural Science Foundation of China under grants 62236005,61936004,and U1913602.
文摘Emotion recognition from physiological signals(ERPS)has drawn tremendous attention and can be potentially applied to numerous fields.Since physiological signals are nonstationary time series with high sampling frequency,it is challenging to directly extract features from them.Additionally,there are 2 major challenges in ERPS:(a)how to adequately capture the correlations between physiological signals at different times and between different types of physiological signals and(b)how to effectively minimize the negative effect caused by temporal covariate shift(TCS).To tackle these problems,we propose a domain generalization and residual network-based approach for emotion recognition from physiological signals(DGR-ERPS).We first pre-extract time-and frequency-domain features from the original time series to compose a new time series.Then,in order to fully extract the correlation information of different physiological signals,these time series are converted into 3D image data to serve as input for a residual-based feature encoder(RBFE).In addition,we introduce a domain generalization-based technique to mitigate the issue posed by TCS.We have conducted extensive experiments on 2 real-world datasets,and the results indicate that our DGR-ERPS achieves superior performance under both TCS and non-TCS scenarios.
文摘In this paper,we first obtain a unified integral representation on the analytic varieties of the general bounded domain in Stein manifolds(the two types bounded domains in[3]are regarded as its special cases).Secondly we get the integral formulas of the solution of∂-equation.And we use a new and unique method to give a uniform estimate of the solution of∂-equation,which is different from Henkin's method.
基金supported by the National Science Fund for Distinguished Young Scholars of China(52025056)the China Postdoctoral Science Foundation(2023M732789)+1 种基金the China Postdoctoral Innovative Talents Support Program(BX20230290)the Fundamental Research Funds for the Central Universities(xzy012022062).
文摘Intelligent machinery fault diagnosis methods have been popularly and successfully developed in the past decades,and the vibration acceleration data collected by contact accelerometers have been widely investigated.In many industrial scenarios,contactless sensors are more preferred.The event camera is an emerging bio-inspired technology for vision sensing,which asynchronously records per-pixel brightness change polarity with high temporal resolution and low latency.It offers a promising tool for contactless machine vibration sensing and fault diagnosis.However,the dynamic vision-based methods suffer from variations of practical factors such as camera position,machine operating condition,etc.Furthermore,as a new sensing technology,the labeled dynamic vision data are limited,which generally cannot cover a wide range of machine fault modes.Aiming at these challenges,a novel dynamic vision-based machinery fault diagnosis method is proposed in this paper.It is motivated to explore the abundant vibration acceleration data for enhancing the dynamic vision-based model performance.A crossmodality feature alignment method is thus proposed with deep adversarial neural networks to achieve fault diagnosis knowledge transfer.An event erasing method is further proposed for improving model robustness against variations.The proposed method can effectively identify unseen fault mode with dynamic vision data.Experiments on two rotating machine monitoring datasets are carried out for validations,and the results suggest the proposed method is promising for generalized contactless machinery fault diagnosis.
文摘As failure data is usually scarce in practice upon preventive maintenance strategy in prognostics and health management(PHM)domain,transfer learning provides a fundamental solution to enhance generalization of datadriven methods.In this paper,we briefly discuss general idea and advances of various transfer learning techniques in PHM domain,including domain adaptation,domain generalization,federated learning,and knowledge-driven transfer learning.Based on the observations from state of the art,we provide extensive discussions on possible challenges and opportunities of transfer learning in PHM domain to direct future development.
基金supported by the National Natural Science Foundation of China(Nos.62225113,62176188,and 623B2080)the Innovative Research Group Project of Hubei Province(No.2024AFA017).
文摘In response to real-world scenarios,the domain generalization(DG)problem has spurred considerable research in person re-identification(ReID).This challenge arises when the target domain,which is significantly different from the source domains,remains unknown.However,the performance of current DG ReID relies heavily on labor-intensive source domain annotations.Considering the potential of unlabeled data,we investigate unsupervised domain generalization(UDG)in ReID.Our goal is to create a model that can generalize from unlabeled source domains to semantically retrieve images in an unseen target domain.To address this,we propose a new approach that trains a domain-agnostic expert(DaE)for unsupervised domain-generalizable person ReID.This involves independently training multiple experts to account for label space inconsistencies between source domains.At the same time,the DaE captures domain-generalizable information for testing.Our experiments demonstrate the effectiveness of this method for learning generalizable features under the UDG setting.The results demonstrate the superiority of our method over state-of-the-art techniques.We will make our code and models available for public use.
基金supported in part by the National Science Foundation under Grants DMS-0807551, DMS-0720925, and DMS-0505473the Natural Science Foundationof China (10728101)supported in part by EPSRC grant EP/F029578/1
文摘We study the initial-boundary value problem of the Navier-Stokes equations for incompressible fluids in a general domain in R^n with compact and smooth boundary, subject to the kinematic and vorticity boundary conditions on the non-flat boundary. We observe that, under the nonhomogeneous boundary conditions, the pressure p can be still recovered by solving the Neumann problem for the Poisson equation. Then we establish the well-posedness of the unsteady Stokes equations and employ the solution to reduce our initial-boundary value problem into an initial-boundary value problem with absolute boundary conditions. Based on this, we first establish the well-posedness for an appropriate local linearized problem with the absolute boundary conditions and the initial condition （without the incompressibility condition）, which establishes a velocity mapping. Then we develop apriori estimates for the velocity mapping, especially involving the Sobolev norm for the time-derivative of the mapping to deal with the complicated boundary conditions, which leads to the existence of the fixed point of the mapping and the existence of solutions to our initial-boundary value problem. Finally, we establish that, when the viscosity coefficient tends zero, the strong solutions of the initial-boundary value problem in R^n（n ≥ 3） with nonhomogeneous vorticity boundary condition converge in L^2 to the corresponding Euler equations satisfying the kinematic condition.
文摘Domain generalizable person re-identification(reid)is a challenging task in computer vision,which aims to apply a trained reid model to unseen domains.Prior works either combine the data in all the training domains to capture domain-invariant features,or adopt a mixture of experts to investigate domain-specific information.In this work,we argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of reid models.To this end,we design a novel framework,which we name two-stream adaptive learning(TAL),to simultaneously model these two kinds of information.Specifically,a domain-specific stream is proposed to capture the training domain statistics with batch normalization(BN)parameters,whereas an adaptive matching layer is designed to dynamically aggregate domain-level information.In the meantime,we design an adaptive BN layer in the domain-invariant stream to approximate the statistic of unseen domains,such that our model is capable of handling various novel scenes.These two streams work adaptively and collaboratively to learn generalizable reid features.As validated by extensive experiments,our framework can be applied to both single-source and multi-source domain generalization tasks,where the results show that our framework notably outperforms the state-of-the-art methods.
基金supported in part by the National Science and Technology Major project,China(No.2022ZD0117901)in part by the National Natural Science Foundation of China(Nos.62373355,62276256 and 62106260).
文摘Generalizable pedestrian attribute recognition(PAR)aims to learn a robust PAR model that can be directly adapted to unknown distributions under varying illumination,different viewpoints and occlusions,which is an essential problem for real-world applications,such as video surveillance and fashion search.In practice,when a trained PAR model is deployed to real-world scenarios,the unseen target samples are fed into the model continuously in an online manner.Therefore,this paper proposes an efficient and flexible method,named AdaGPAR,for generalizable PAR(GPAR)via test-time adaptation(TTA),where we adapt the trained model through exploiting the unlabeled target samples online during the test phase.As far as we know,it is the first work that solves the GPAR from the perspective of TTA.In particular,the proposed AdaGPAR memorizes the reliable target sample pairs(features and pseudo-labels)as prototypes gradually in the test phase.Then,it makes predictions with a non-parametric classifier by calculating the similarity between a target instance and the prototypes.However,since PAR is a task of multi-label classification,only using the same holistic feature of one pedestrian image as the prototypes of multiple attributes is not optimal.Therefore,an attribute localization branch is introduced to extract the attribute-specific features,where two kinds of memory banks are further constructed to cache the global and attribute-specific features simultaneously.In summary,the AdaGPAR is training-free in the test phase and predicts multiple pedestrian attributes of the target samples in an online manner.This makes the AdaGPAR time efficient and generalizable for real-world applications.Extensive experiments have been performed on the UPAR benchmark to compare the proposed method with multiple baselines.The superior performance demonstrates the effectiveness of the proposed AdaGPAR that improves the generalizability of a PAR model via TTA.
基金supported by the National Natural Science Foundation of China(Nos.62373360 and 62473368).
文摘Gear pitting fault is a common issue in gear systems,affecting transmission efficiency and potentially leading to severe equipment shutdowns.Effective diagnosis enhances reliability,reduces maintenance costs,and extends equipment lifespan.However,existing deep learning based methods often neglect the inherent structure of temporal vibration signals and fail to address domain variations,resulting in poor generalization and performance.To overcome these limitations,we propose a novel approach based on domain-independent features.Vibration signals are mapped to time-frequency representations via short-time Fourier transform,and dependencies between different frequencies are effectively captured using a Transformer encoder.The proposed method incorporates a feature decoupling structure that combines singular value decomposition and Pearson correlation coefficient to extract low-rank approximations of domain-related and pitting-related features,while quantifying their correlation.This approach mitigates feature degradation in constructing domain-independent features.Additionally,the weighted LinSoftmax function is introduced as a replacement for the traditional Softmax,leading to a more stable optimization target and improved model accuracy,with a distance-based penalty weight focusing on significant prediction errors.Experiments on the 2023 PHM Data Challenge dataset demonstrate the effectiveness of the proposed method,achieving a mean absolute error of 0.11,an accuracy of 92.32%,and a fault tolerance accuracy of 98.02%.
基金the U.S.National Science Foundation(NSF)Division of Civil,Mechanical and Manufacturing Innovation(grant number 1463493)Transportation Research Board of The National Academies-IDEA Project 222,and National Aeronautics and Space Administration(NASA)Award No.80NSSC20K0326 for the research activities and particularly for this paper.
文摘Implementing Structural Health Monitoring(SHM)systems with extensive sensing layouts on all civil structures is obviously expensive and unfeasible.Thus,estimating the state(condition)of dissimilar civil structures based on the information collected from other structures is regarded as a useful and essential way.For this purpose,Structural State Translation(SST)has been recently proposed to predict the response data of civil structures based on the information acquired from a dissimilar structure.This study uses the SST methodology to translate the state of one bridge(Bridge#1)to a new state based on the knowledge acquired from a structurally dissimilar bridge(Bridge#2).Specifically,the Domain-Generalized Cycle-Generative(DGCG)model is trained in the Domain Generalization learning approach on two distinct data domains obtained from Bridge#1;the bridges have two different conditions:State-H and State-D.Then,the model is used to generalize and transfer the knowledge on Bridge#1 to Bridge#2.In doing so,DGCG translates the state of Bridge#2 to the state that the model has learned after being trained.In one scenario,Bridge#2’s State-H is translated to State-D;in another scenario,Bridge#2’s State-D is translated to State-H.The translated bridge states are then compared with the real ones via modal identifiers and mean magnitude-squared coherence(MMSC),showing that the translated states are remarkably similar to the real ones.For instance,the modes of the translated and real bridge states are similar,with the maximum frequency difference of 1.12%and the minimum correlation of 0.923 in Modal Assurance Criterion values,as well as the minimum of 0.947 in Average MMSC values.In conclusion,this study demonstrates that SST is a promising methodology for research with data scarcity and population-based structural health monitoring(PBSHM).In addition,a critical discussion about the methodology adopted in this study is also offered to address some related concerns.
基金The authors were partially supported by the National Natural Science Foundation of China （No.11371042）.
文摘In this paper, we consider the viscous incompressible magnetohydrodynamic （MHD） system with a new boundary condition for a general smooth domain in R^3. We obtain the well-posedness of the system and the vanishing viscosity limit result.
