Hui Xu
Hui Xu has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Xin Wang
Hefei University of Technology,Hefei,China,230601
2 shared publications - Chen Jiang
Ant Group Company Ltd., Hangzhou, China
1 shared publication Chujiao Wang
School of Computer Science and Technology China University of Mining and Technology 221116 Xuzhou Jiangsu China
1 shared publication- Chunguang Li
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
1 shared publication - Enhui Shi
Nanjing Normal University
1 shared publication - Feng Qian
East China University of Science and Technology
1 shared publication
Latest Publications
- 22 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Research on Object Detection in Unmanned Aerial Vehicle Aerial Images Based on Improved YOLOv7
In addressing challenges such as significant variations in target scales, limited accuracy in detecting small objects, and elevated omission rates in scenes captured by unmanned aerial vehicles, this study introduces an enhanced YOLOv7 object detection algorithm. Firstly, an additional small object detection layer is incorporated into the original YOLOv7 to adapt to object targets across different scales, thereby reducing the omission rate of small objects. Secondly, a parameter-free attention mechanism is introduced into the feature fusion network. Based on this attention mechanism, a Triplet Attention module is constructed to enhance the integration of more critical feature information within the network. Lastly, the loss function CIoU is replaced by WIoUv1 to further improve the convergence speed and detection accuracy of the model. Experimental results demonstrate the excellence of this model on the VisDrone dataset, achieving an mAP of 49.5% on the test set. Compared to the baseline YOLOv7 model, this proposed algorithm exhibits a 2.2% improvement and notably enhances the detection performance of small objects.
- 22 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Research on Object Detection in Unmanned Aerial Vehicle Aerial Images Based on Improved YOLOv7
In addressing challenges such as significant variations in target scales, limited accuracy in detecting small objects, and elevated omission rates in scenes captured by unmanned aerial vehicles, this study introduces an enhanced YOLOv7 object detection algorithm. Firstly, an additional small object detection layer is incorporated into the original YOLOv7 to adapt to object targets across different scales, thereby reducing the omission rate of small objects. Secondly, a parameter-free attention mechanism is introduced into the feature fusion network. Based on this attention mechanism, a Triplet Attention module is constructed to enhance the integration of more critical feature information within the network. Lastly, the loss function CIoU is replaced by WIoUv1 to further improve the convergence speed and detection accuracy of the model. Experimental results demonstrate the excellence of this model on the VisDrone dataset, achieving an mAP of 49.5% on the test set. Compared to the baseline YOLOv7 model, this proposed algorithm exhibits a 2.2% improvement and notably enhances the detection performance of small objects.
- Open Access
An Incentive Mechanism for Federated Learning Based on Multiple Resource Exchange
Federated Learning (FL) is a distributed machine learning paradigm that addresses privacy concerns in machine learning and still guarantees high test accuracy. However, achieving the necessary accuracy by having all clients participate in FL is impractical, given the constraints of client local computing resource. In this paper, we introduce a multi-user collaborative computing framework, categorizing users into two roles: model owners (MOs) and data owner (DOs). Without resorting to monetary incentives, an MO can encourage more DOs to join in FL by allowing the DOs to offload extra local computing tasks to the MO for execution. This exchange of "data" for "computing resources" streamlines the incentives for clients to engage more effectively in FL. We formulate the interaction between MO and DOs as an optimization problem, and the objective is to effectively utilize the communication and computing resource of the MO and DOs to minimize the time to complete an FL task. The proposed problem is a mixed integer nonlinear programming (MINLP) with high computational complexity. We first decompose it into two distinct subproblems, namely the client selection problem and the resource allocation problem to segregate the integer variables from the continuous variables. Then, an effective iterative algorithm is proposed to solve problem. Simulation results demonstrate that the proposed collaborative computing framework can achieve an accuracy of more than 95\% while minimizing the overall time to complete an FL task.
Open AccessAn Incentive Mechanism for Federated Learning Based on Multiple Resource Exchange
Federated Learning (FL) is a distributed machine learning paradigm that addresses privacy concerns in machine learning and still guarantees high test accuracy. However, achieving the necessary accuracy by having all clients participate in FL is impractical, given the constraints of client local computing resource. In this paper, we introduce a multi-user collaborative computing framework, categorizing users into two roles: model owners (MOs) and data owner (DOs). Without resorting to monetary incentives, an MO can encourage more DOs to join in FL by allowing the DOs to offload extra local computing tasks to the MO for execution. This exchange of "data" for "computing resources" streamlines the incentives for clients to engage more effectively in FL. We formulate the interaction between MO and DOs as an optimization problem, and the objective is to effectively utilize the communication and computing resource of the MO and DOs to minimize the time to complete an FL task. The proposed problem is a mixed integer nonlinear programming (MINLP) with high computational complexity. We first decompose it into two distinct subproblems, namely the client selection problem and the resource allocation problem to segregate the integer variables from the continuous variables. Then, an effective iterative algorithm is proposed to solve problem. Simulation results demonstrate that the proposed collaborative computing framework can achieve an accuracy of more than 95\% while minimizing the overall time to complete an FL task.
- 15 November 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Wavelets, Multiresolution and Information Processing
- Vol. 22 (03)
Community detection: Concepts, algorithms, evaluation and challenges
Recently, research on complex networks has become a hot topic. Community detection, as a main task in social network analysis, plays an important role in complex networks. In this paper, we survey and summarize the development and trend of community detection and analyze typical algorithms presented in recent years. We first discuss the algorithms from algorithmic thinking, key technology and the advantages and disadvantages. Second, evaluation metrics and datasets are introduced. Finally, some application scenarios are pointed out for the potential application in the future. It is hoped that this review will serve as the steppingstone for those interested in community detection.
- 15 November 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Wavelets, Multiresolution and Information Processing
- Vol. 22 (03)
Community detection: Concepts, algorithms, evaluation and challenges
Recently, research on complex networks has become a hot topic. Community detection, as a main task in social network analysis, plays an important role in complex networks. In this paper, we survey and summarize the development and trend of community detection and analyze typical algorithms presented in recent years. We first discuss the algorithms from algorithmic thinking, key technology and the advantages and disadvantages. Second, evaluation metrics and datasets are introduced. Finally, some application scenarios are pointed out for the potential application in the future. It is hoped that this review will serve as the steppingstone for those interested in community detection.
- Open Access
A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale, VCSL not only has two orders of magnitude more segment-level labelled data, with 160k realistic video copy pairs containing more than 280k localized copied segment pairs, but also covers a variety of video categories and a wide range of video duration. All the copied segments inside each collected video pair are manually extracted and accompanied by precisely annotated starting and ending timestamps. Alongside the dataset, we also propose a novel evaluation protocol that better measures the prediction accuracy of copy overlapping segments between a video pair and shows improved adaptability in different scenarios. By benchmarking several baseline and state-of-the-art segment-level video copy detection methods with the proposed dataset and evaluation metric, we provide a comprehensive analysis that uncovers the strengths and weaknesses of current approaches, hoping to open up promising directions for future works. The VCSL dataset, metric and benchmark codes are all publicly available at https://github.com/alipay/VCSL.
Open AccessA Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset. Compared with existing copy detection datasets restricted by either video-level annotation or small-scale, VCSL not only has two orders of magnitude more segment-level labelled data, with 160k realistic video copy pairs containing more than 280k localized copied segment pairs, but also covers a variety of video categories and a wide range of video duration. All the copied segments inside each collected video pair are manually extracted and accompanied by precisely annotated starting and ending timestamps. Alongside the dataset, we also propose a novel evaluation protocol that better measures the prediction accuracy of copy overlapping segments between a video pair and shows improved adaptability in different scenarios. By benchmarking several baseline and state-of-the-art segment-level video copy detection methods with the proposed dataset and evaluation metric, we provide a comprehensive analysis that uncovers the strengths and weaknesses of current approaches, hoping to open up promising directions for future works. The VCSL dataset, metric and benchmark codes are all publicly available at https://github.com/alipay/VCSL.
- Open AccessThe nonexistence of expansive polycyclic group actions on the circle $\mathbb S^1$We show that the circle $\mathbb S^1$ admits no expansive polycyclic group actions.Open AccessThe nonexistence of expansive polycyclic group actions on the circle $\mathbb S^1$We show that the circle $\mathbb S^1$ admits no expansive polycyclic group actions.
- Open Access
Cauchy, normal and correlations versus heavy tails
A surprising result of Pillai and Meng (2016) showed that a transformation $\sum_{j=1}^n w_j X_j/Y_j$ of two iid centered normal random vectors, $(X_1,\ldots, X_n)$ and $(Y_1,\ldots, Y_n)$, $n>1$, for any weights $0\leq w_j\leq 1$, $ j=1,\ldots, n$, $\sum_{j=1}^n w_j=1$, has a Cauchy distribution regardless of any correlations within the normal vectors. The correlations appear to lose out in the competition with the heavy tails. To clarify how extensive this phenomenon is, we analyze two other transformations of two iid centered normal random vectors. These transformations are similar in spirit to the transformation considered by Pillai and Meng (2016). One transformation involves absolute values: $\sum_{j=1}^n w_j X_j/|Y_j|$. The second involves randomly stopped Brownian motions: $\sum_{j=1}^n w_j X_j\bigl(Y_j^{-2}\bigr)$, where $\bigl\{\bigl( X_1(t),\ldots, X_n(t)\bigr), \, t\geq 0\bigr\},\ n>1,$ is a Brownian motion with positive variances; $(Y_1,\ldots, Y_n)$ is a centered normal random vector with the same law as $( X_1(1),\ldots, X_n(1))$ and independent of it; and $X(Y^{-2})$ is the value of the Brownian motion $X(t)$ evaluated at the random time $t=Y^{-2}$. All three transformations result in a Cauchy distribution if the covariance matrix of the normal components is diagonal, or if all the correlations implied by the covariance matrix equal 1. However, while the transformation Pillai and Meng (2016) considered produces a Cauchy distribution regardless of the normal covariance matrix. the transformations we consider here do not always produce a Cauchy distribution. The correlations between jointly normal random variables are not always overwhelmed by the heaviness of the marginal tails. The mysteries of the connections between normal and Cauchy laws remain to be understood.Open AccessCauchy, normal and correlations versus heavy tails
A surprising result of Pillai and Meng (2016) showed that a transformation $\sum_{j=1}^n w_j X_j/Y_j$ of two iid centered normal random vectors, $(X_1,\ldots, X_n)$ and $(Y_1,\ldots, Y_n)$, $n>1$, for any weights $0\leq w_j\leq 1$, $ j=1,\ldots, n$, $\sum_{j=1}^n w_j=1$, has a Cauchy distribution regardless of any correlations within the normal vectors. The correlations appear to lose out in the competition with the heavy tails. To clarify how extensive this phenomenon is, we analyze two other transformations of two iid centered normal random vectors. These transformations are similar in spirit to the transformation considered by Pillai and Meng (2016). One transformation involves absolute values: $\sum_{j=1}^n w_j X_j/|Y_j|$. The second involves randomly stopped Brownian motions: $\sum_{j=1}^n w_j X_j\bigl(Y_j^{-2}\bigr)$, where $\bigl\{\bigl( X_1(t),\ldots, X_n(t)\bigr), \, t\geq 0\bigr\},\ n>1,$ is a Brownian motion with positive variances; $(Y_1,\ldots, Y_n)$ is a centered normal random vector with the same law as $( X_1(1),\ldots, X_n(1))$ and independent of it; and $X(Y^{-2})$ is the value of the Brownian motion $X(t)$ evaluated at the random time $t=Y^{-2}$. All three transformations result in a Cauchy distribution if the covariance matrix of the normal components is diagonal, or if all the correlations implied by the covariance matrix equal 1. However, while the transformation Pillai and Meng (2016) considered produces a Cauchy distribution regardless of the normal covariance matrix. the transformations we consider here do not always produce a Cauchy distribution. The correlations between jointly normal random variables are not always overwhelmed by the heaviness of the marginal tails. The mysteries of the connections between normal and Cauchy laws remain to be understood. - Open Access
Thickness Distribution Prediction for Tectonically Deformed Coal with a Deep Belief Network: A Case Study
Thickness of tectonically deformed coal (TDC) has positive correlations with the susceptible gas outbursts in coal mines. To predict the TDC thickness of the coalbed, we proposed a prediction method using seismic attributes based on the deep belief network (DBN) and dimensionality reduction. Firstly, we built a DBN prediction model using the extracted attributes from a synthetic seismic section. Next, we transformed the possibly correlated seismic attributes into principal components through principal components analysis. Then, we compared the true TDC thickness with the predicted TDC thicknesses to evaluate the prediction accuracy of different models, i.e., a DBN model, a support vector machine model, and an extreme learning machine model. Finally, we used the DBN model to predict the TDC thickness of coalbed No. 8 in an operational coal mine based on synthetic experiments. Our studies showed that the predicted distribution of TDC thickness followed the regional characteristics of TDC development well and was positively correlated with the burial depth, coalbed thickness, and tectonic development. In summary, the proposed DBN model provided a reliable method for predicting TDC thickness and reducing gas outbursts in coal mine operations.
Open AccessThickness Distribution Prediction for Tectonically Deformed Coal with a Deep Belief Network: A Case Study
Thickness of tectonically deformed coal (TDC) has positive correlations with the susceptible gas outbursts in coal mines. To predict the TDC thickness of the coalbed, we proposed a prediction method using seismic attributes based on the deep belief network (DBN) and dimensionality reduction. Firstly, we built a DBN prediction model using the extracted attributes from a synthetic seismic section. Next, we transformed the possibly correlated seismic attributes into principal components through principal components analysis. Then, we compared the true TDC thickness with the predicted TDC thicknesses to evaluate the prediction accuracy of different models, i.e., a DBN model, a support vector machine model, and an extreme learning machine model. Finally, we used the DBN model to predict the TDC thickness of coalbed No. 8 in an operational coal mine based on synthetic experiments. Our studies showed that the predicted distribution of TDC thickness followed the regional characteristics of TDC development well and was positively correlated with the burial depth, coalbed thickness, and tectonic development. In summary, the proposed DBN model provided a reliable method for predicting TDC thickness and reducing gas outbursts in coal mine operations.
- Open Access
No-Reference Quality Assessment Method for Blurriness of SEM Micrographs with Multiple Texture
Scanning electron microscopy (SEM) plays an important role in the intuitive understanding of microstructures because it can provide ultrahigh magnification. Tens or hundreds of images are regularly generated and saved during a typical microscopy imaging process. Given the subjectivity of a microscopist’s focusing operation, blurriness is an important distortion that debases the quality of micrographs. The selection of high-quality micrographs using subjective methods is expensive and time-consuming. This study proposes a new no-reference quality assessment method for evaluating the blurriness of SEM micrographs. The human visual system is more sensitive to the distortions of cartoon components than to those of redundant textured components according to the Gestalt perception psychology and the entropy masking property. Micrographs are initially decomposed into cartoon and textured components. Then, the spectral and spatial sharpness maps of the cartoon components are extracted. One metric is calculated by combining the spatial and spectral sharpness maps of the cartoon components. The other metric is calculated on the basis of the edge of the maximum local variation map of the cartoon components. Finally, the two metrics are combined as the final metric. The objective scores generated using this method exhibit high correlation and consistency with the subjective scores.
Open AccessNo-Reference Quality Assessment Method for Blurriness of SEM Micrographs with Multiple Texture
Scanning electron microscopy (SEM) plays an important role in the intuitive understanding of microstructures because it can provide ultrahigh magnification. Tens or hundreds of images are regularly generated and saved during a typical microscopy imaging process. Given the subjectivity of a microscopist’s focusing operation, blurriness is an important distortion that debases the quality of micrographs. The selection of high-quality micrographs using subjective methods is expensive and time-consuming. This study proposes a new no-reference quality assessment method for evaluating the blurriness of SEM micrographs. The human visual system is more sensitive to the distortions of cartoon components than to those of redundant textured components according to the Gestalt perception psychology and the entropy masking property. Micrographs are initially decomposed into cartoon and textured components. Then, the spectral and spatial sharpness maps of the cartoon components are extracted. One metric is calculated by combining the spatial and spectral sharpness maps of the cartoon components. The other metric is calculated on the basis of the edge of the maximum local variation map of the cartoon components. Finally, the two metrics are combined as the final metric. The objective scores generated using this method exhibit high correlation and consistency with the subjective scores.
- Open Access
- 14 January 2019
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2019 (1)
Multiple Kernel Dimensionality Reduction via Ratio‐Trace and Marginal Fisher Analysis
Traditional supervised multiple kernel learning (MKL) for dimensionality reduction is generally an extension of kernel discriminant analysis (KDA), which has some restrictive assumptions. In addition, they generally are based on graph embedding framework. A more general multiple kernel‐based dimensionality reduction algorithm, called multiple kernel marginal Fisher analysis (MKL‐MFA), is presented for supervised nonlinear dimensionality reduction combined with ratio‐race optimization problem. MKL‐MFA aims at relaxing the restrictive assumption that the data of each class is of a Gaussian distribution and finding an appropriate convex combination of several base kernels. To improve the efficiency of multiple kernel dimensionality reduction, the spectral regression frameworks are incorporated into the optimization model. Furthermore, the optimal weights of predefined base kernels can be obtained by solving a different convex optimization. Experimental results on benchmark datasets demonstrate that MKL‐MFA outperforms the state‐of‐the‐art supervised multiple kernel dimensionality reduction methods.
- 14 January 2019
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2019 (1)
Open AccessMultiple Kernel Dimensionality Reduction via Ratio‐Trace and Marginal Fisher Analysis
Traditional supervised multiple kernel learning (MKL) for dimensionality reduction is generally an extension of kernel discriminant analysis (KDA), which has some restrictive assumptions. In addition, they generally are based on graph embedding framework. A more general multiple kernel‐based dimensionality reduction algorithm, called multiple kernel marginal Fisher analysis (MKL‐MFA), is presented for supervised nonlinear dimensionality reduction combined with ratio‐race optimization problem. MKL‐MFA aims at relaxing the restrictive assumption that the data of each class is of a Gaussian distribution and finding an appropriate convex combination of several base kernels. To improve the efficiency of multiple kernel dimensionality reduction, the spectral regression frameworks are incorporated into the optimization model. Furthermore, the optimal weights of predefined base kernels can be obtained by solving a different convex optimization. Experimental results on benchmark datasets demonstrate that MKL‐MFA outperforms the state‐of‐the‐art supervised multiple kernel dimensionality reduction methods.
- Open Access
- 3 January 2018
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 12 (4) , 377-383
NSCT‐PCNN image fusion based on image gradient motivation
Pulse coupled neural network (PCNN) is widely used in image processing because of its unique biological characteristics, which is suitable for image fusion. When combining PCNN with non‐subsampled contourlet (NSCT) model, it is applied in overcoming the difficulty of coefficients selection for subband of the NSCT model. However in the original model, only the grey values of image pixels are used as input, without considering that the subjective vision of human eyes lacks the sensitivity to the local factors of the image. In this study, the improved pulse‐coupled neural network model has replaced the grey‐scale value of the image and introduced the weighted product of the strength of the gradient of the image and the local phase coherence as the model input. Finally, compared with other multi‐scale decompositions‐based image fusion and other improved NSCT‐PCNN algorithms, the algorithm presented in this study outperforms them in terms of objective criteria and visual appearance.
- 3 January 2018
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 12 (4) , 377-383
Open AccessNSCT‐PCNN image fusion based on image gradient motivation
Pulse coupled neural network (PCNN) is widely used in image processing because of its unique biological characteristics, which is suitable for image fusion. When combining PCNN with non‐subsampled contourlet (NSCT) model, it is applied in overcoming the difficulty of coefficients selection for subband of the NSCT model. However in the original model, only the grey values of image pixels are used as input, without considering that the subjective vision of human eyes lacks the sensitivity to the local factors of the image. In this study, the improved pulse‐coupled neural network model has replaced the grey‐scale value of the image and introduced the weighted product of the strength of the gradient of the image and the local phase coherence as the model input. Finally, compared with other multi‐scale decompositions‐based image fusion and other improved NSCT‐PCNN algorithms, the algorithm presented in this study outperforms them in terms of objective criteria and visual appearance.