检索结果-内蒙古大学图书馆

GNN-Assisted BiG-AMP: Joint Channel Estimation and Data Detection for Massive MIMO Receiver

学校读者我要写书评

暂无评论

IEEE Transactions on Wireless Communications 2025年

作者： Liu, Zishen Wu, Nan He, Dongxuan Yuan, Weijie Li, Yonghui Quek, Tony Q. S. School of Information and Electronics Beijing Institute of Technology Beijing100081 China School of System Design and Intelligent Manufacturing Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2008 Australia Singapore University of Technology and Design 487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of

In this paper, we develop a graph neural network (GNN)-assisted bilinear inference approach to enhance the receiver performance of the MIMO system through message passing-based joint channel estimation and data detection (JCD). Specifically, based on the bilinear generalized approximate message passing (BiG-AMP) framework and conditional correlation of signal, we propose a GNN-assisted BiG-AMP (GNN-BiGAMP) approach, which integrates a GNN module into the data-detection-loop to compensate the inaccurate marginal likelihood approximation. By leveraging the coupling between the channel and received symbols, a bilinear GNN-assisted BiG-AMP (BiGNN-BiGAMP) JCD receiver is further proposed. This method incorporates two GNNs with similar graph representation into the bilinear posterior estimation loops, which not only compensates for approximation errors but also alleviates performance loss due to premature variance convergence, thereby enhancing the receiver performance significantly. To fully exploit the supervised information from channel estimation and data detection, we propose a multitask learning based training scheme, which coordinates GNNs with different tasks in two loops. Simulation results show that our proposed GNN-assisted JCD receivers significantly outperform other JCD counterparts in terms of both channel estimation and data detection. © 2025 IEEE. All rights reserved.

关键词： Graph neural networks

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Dee...

IEEE International Conference on Automated Software Engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zhen Zhang, Ruqian Zou, Deqing Wang, Ning Li, Yating Xu, Shouhuai Chen, Chen Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Colorado Colorado Springs United States Center for Research in Computer Vision University of Central Florida United States School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier;the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

Multi-block SSD based on small object detection for UAV railway scene surveillance

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2020年第6期33卷 1747-1755页

作者： Yundong LI Han DONG Hongguang LI Xueyan ZHANG Baochang ZHANG Zhifeng XIAO North China University of Technology Beijing 100144China Key Laboratory of Large Structure Health Monitoring and Control Shijiazhuang 050043China Unmanned System Research Institute Beihang UniversityBeijing 100083China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100083China State Key Laboratory of Information Engineering in Surveying Wuhan UniversityWuhan 430079China

A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle *** address the limitation of small object detection,a multi-block SSD mechanism,which consists of three steps,is ***,the original input images are segmented into several overlapped ***,each patch is separately fed into an SSD to detect the ***,the patches are merged together through two *** the first stage,the truncated object of the sub-layer detection result is *** the second stage,a sub-layer suppression and filtering algorithm applying the concept of non-maximum suppression is utilized to remove the overlapped boxes of *** boxes that are not detected in the main-layer are *** addition,no sufficient labeled training samples of railway circumstance are available,thereby hindering the deployment of SSD.A two-stage training strategy leveraging to transfer learning is adopted to solve this *** deep learning model is preliminarily trained using labeled data of numerous auxiliaries,and then it is refined using only a few samples of railway scene.A railway spot in China,which is easily damaged by landslides,is investigated as a case *** results show that the proposed multi-block SSD method produces an overall accuracy of 96.6%and obtains an improvement of up to 9.2%compared with the traditional SSD.

关键词： Deep learning Multi-block Single Shot MultiBox Detector(SSD) Objection detection Railway scene Unmanned aerial vehicle remote sensing

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

New Method of Traffic Flow Forecasting Based on QPSO Strategy for Internet of Vehicles 4

学校读者我要写书评

暂无评论

New Method of Traffic Flow Forecasting Based on QPSO Strateg...

4th IEEE International Conference on Smart Internet of Things, SmartIoT 2020

作者： Zhang, De-Gan Du, Jing-Yu Zhang, Ting Fan, Hong-Rui Tianjin University of Technology Tianjin Key Lab of Intelligent Computing Novel Software Technology Tianjin300384 China Tianjin University of Technology Ministry of Education Key Laboratory of Computer Vision and System Tianjin China

ISBN: (纸本)9781728165141

We propose a new method of traffic flow forecasting based on quantum particle swarm optimization strategy (QPSO) for Internet of Vehicles (IOV). Establish a corresponding model based on the characteristics of the traffic flow data. The genetic simulated annealing method is applied to the quantum particle swarm method to obtain the optimized initial cluster center, and is applied to the parameter optimization of the radial basis neural network prediction model. The function approximation of radial basis neural network can be used to obtain the required data. In addition, in order to compare the performance of the methods, a comparison study with other related methods such as QPSO-RBF is also performed. Our method can reduce prediction errors and get better and more stable prediction results. © 2020 IEEE.

关键词： Forecasting

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Novel Resource Allocation Algorithm of Edge Computing Based on Deep Reinforcement Learning Mechanism

学校读者我要写书评

暂无评论

Novel Resource Allocation Algorithm of Edge Computing Based ...

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Degan Zhang Hongrui Fan Jie Zhang Key Laboratory of Computer Vision and System (Ministry of Education) Tianjin University of Technology Tianjin China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

Edge computing is a computing paradigm that can bring practical value to most modern enterprises. When it is integrated into the Internet of Things system, it can improve the QoS of mobile applications, and can realize real-time management of the generated big data.5G promotes the development of the edge computing paradigm further, and mobile users can obtain low-latency and high-speed access QoS. In this paper, we study the resource allocation method of edge servers in the MEC environment. We are absorbed in solving the problem of allocation of limited resources in the MEC system, such as computing resources and available bandwidth, with the goal of maximizing the average resource utilization and task processing capacity of edge servers in the MEC system, while considering some differential processing for delay-sensitive applications, describe this resource allocation problem as a Finite-state Markov Decision Process (FMDP), and consider the continuity of the user state, and design a new Edge Computing Resource Allocation Algorithm based on Deep Deterministic Policy Gradient (ECRAA-DDPG)to find the optimal strategy for resource allocation. Finally, a large number of experiments are used to prove the performance of the new algorithm, and the experimental results show that the method can make the optimal decision in a real environment.

关键词： Reinforcement learning Quality of service Markov processes Real-time systems Mobile applications Resource management Servers