检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Temporal-Assisted Beamforming and Trajectory Prediction in Sensing-Enabled UAV Communications

引用

IEEE Transactions on Communications 2024年

作者： Zhou, Shengcai Yang, Halvin Xiang, Luping Yang, Kun University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China University College London Department of Electronic and Electrical Engineering LondonWClE 7JE United Kingdom Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China Nanjing University Suzhou Campus School of Intelligent Software and Engineering Suzhou215163 China

In the evolving landscape of high-speed communication, the shift from traditional pilot-based methods to a Sensing-Oriented Approach (SOA) is anticipated to gain momentum. This paper delves into the development of an innovative Integrated Sensing and Communication (ISAC) framework, specifically tailored for beamforming and trajectory prediction processes. Central to this research is the exploration of an Unmanned Aerial Vehicle (UAV)-enabled communication system, which seamlessly integrates ISAC technology. This integration underscores the synergistic interplay between sensing and communication capabilities. The proposed system initially deploys omnidirectional beams for the sensing-focused phase, subsequently transitioning to directional beams for precise object tracking. This process incorporates an Extended Kalman Filtering (EKF) methodology for the accurate estimation and prediction of object states. A novel frame structure is introduced, employing historical sensing data to optimize beamforming in real-time for subsequent time slots, a strategy we refer to as 'temporal-assisted' beamforming. To refine the temporal-assisted beamforming technique, we employ Successive Convex Approximation (SCA) in tandem with Iterative Rank Minimization (IRM), yielding high-quality suboptimal solutions. Comparative analysis with conventional pilot-based systems reveals that our approach yields a substantial improvement of 156% in multi-object scenarios and 136% in single-object scenarios. © 1972-2012 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A Robust Method for Tdoa-Based Localization and Tracking in Real Indoor Environment

SSRN

引用

SSRN 2022年

作者： Mei, Hong-Yuan Zhou, Zhi Shen, Fu-Rao Zhao, Jian School of Artificial Intelligence Nanjing University China State Key Laboratory for Novel Software Technology Nanjing China Department of Computer Science and Technology Nanjing University China School of Electronic Science and Engineering Nanjing University China

Great efforts have been made to deal with localization based on time-difference-of-arrival (TDOA) measurements in the past decades. It is widely used in applications such as radar, sonar, sensor networks, and mobile communications. However, such a task is still challenging in complex real-world scenarios where large-scale noise and none-light-of-sight (NLOS) occur. To address this challenge, we propose a noise-tolerant method consisting of two stages: Robust Multilateration Solver (RMS) and Restricted Particle Filter (RPF). In the first stage, anomaly detection is adopted to eliminate outliers and NLOS effects are mitigated by a data augmentation strategy. Then a rough estimate of the current position is obtained by a combination of two modified multilateration algorithms. In the second stage, the rough estimate is passed through an enhanced particle filter in order to reduce its bias caused by heavy Gaussian noise and smooth the motion trajectory. Meanwhile, the localization rationality is guaranteed by confining the position to a predefined area. Sufficient testing in real indoor environments and simulation results demonstrate the effectiveness of our method, revealing its fitness for various industrial fields. © 2022, The Authors. All rights reserved.

关键词： Time difference of arrival

来源：评论

学校读者我要写书评

暂无评论

Integrating Exact Simulation into Sweeping for Datapath Combinational Equivalence Checking

Integrating Exact Simulation into Sweeping for Datapath Comb...

引用

IEEE International Conference on computer-Aided Design

作者： Zhihan Chen Xindi Zhang Yuhang Qian Qiang Xu Shaowei Cai School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science & Engineering The Chinese University of Hong Kong

In the application of IC design for microprocessors, there are often demands for optimizing the implementation of datapath circuits, on which various arithmetic operations are performed. Combinational equivalence checking (CEC) plays an essential role in ensuring the correctness of design optimization. The most prevalent CEC algorithms are based on SAT sweeping, which utilizes SAT to prove the equivalence of the internal node pairs in topological order, and the equivalent nodes are merged. Datapath circuits usually contain equivalent pairs for which the transitive fan-in cones are small but have a high XOR chain density, and proving such node pairs is very difficult for SAT solvers. An exact probability-based simulation (EPS) is suitable for verifying such pairs, while this method is not suitable for pairs with many primary inputs due to the memory cost. We first reduce the memory cost of EPS and integrate it to improve the SAT sweeping method. Considering the complementary abilities of SAT and EPS, we design an engine selection heuristic to dynamically choose SAT or EPS in the sweeping process, according to XOR chain density. Our method is further improved by reducing unnecessary engine calls by detecting regularity. Experiments on a benchmark suite from industrial datapath circuits show that our method is much faster than the state-of-the-art CEC tool namely ABC ‘&cec’ on nearly all instances, and is more than 100× faster on 30% of the instances, 1000× faster on 12% of the instances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Perception for Unified Visual Multi-modal Object Tracking

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Hu, Xiantao Zhong, Bineng Liang, Qihua Shi, Liangtao Mo, Zhiyi Tai, Ying Yang, Jian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Guilin541004 China Guangxi Normal University Security Guilin541004 China Guangxi Normal University Intelligent Technology Guilin541004 China Guangxi Normal University Ministry of Education Guilin541004 China Wuzhou University School of Data Science Wuzhou543002 China Wuzhou University Software Engineering Wuzhou543002 China Nanjing University State Key Laboratory for Novel Software Technology Suzhou215163 China Nanjing University of Science and Technology School of Computer Science Nanjing210094 China Nanjing University of Science and Technology Engineering Nanjing210094 China

Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. © 2020 IEEE.

关键词： Multicarrier modulation

来源：评论

学校读者我要写书评

暂无评论

FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection 39

FakeDiffer: Distributional Disparity Learning on Differentia...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Bo Zhang, Zhao Zhao, Suiyi Ye, Xianming Zhang, Haijun Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Yunnan China Department of Electronic and Computer Engineering University of Pretoria South Africa Shenzhen China

ISBN: (纸本)157735897X

Existing face forgery detection methods achieve promising performance when training and testing forgery data are from identical manipulation types, while they fail to generalize well to unseen samples. In this paper, we experimentally investigate and find that the poor generalization of the methods mainly arises from their overfitting on the known fake patterns. Excessively focused on seen fakes, those detectors fail to effectively learn image-intrinsic information and the distributional disparity between real and fake images. Then, to address this issue, we redefine fake learning as real-fake distributional disparity learning. We propose a novel deepfake detection framework learning distributional disparity based on the differentiated reconstruction on real and fake images for improved generalization. Specifically, distributional disparity learning on differentiated reconstruction of the real and fake images, enforces the model to learn image-invariant intrinsic representations. The reconstruction on real and fake images forces the decoders to learn the distribution of real and fake images, respectively. Moreover, to avoid the influence from the specificalization of the known fake patterns, we further propose the information interaction learning on the encoded intrinsic information and the pixel disparity between the input image and its reconstruction to distinguish face forgeries that are even unknown. Extensive experiments on large-scale benchmark datasets demonstrated the effectiveness of addressing the overfitting issue of the classification network, and verified the superior performance of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enabling Generalized Zero-Shot Vulnerability Classification

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Hu, Jinghao Guo, Jinsong Luo, Chen Hu, Yang Lanzinger, Matthias Li, Zhanshan Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Software Changchun130012 China University College London Department of Computer Science United Kingdom Amazon United States United Kingdom University of Oxford Department of Computer Science United Kingdom Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Changchun130012 China

Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces VulnSense, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. VulnSense learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, VulnSense learns from three main resources: (1) seen classes with labeled code instances;(2) descriptions of these seen classes;and (3) descriptions of "unseen"classes which have no labeled instances. Our experiments underscore VulnSense's superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. VulnSense demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work. © 2004-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Improving Write Performance for LSM-tree-based key-Value Stores with NV-Cache

Improving Write Performance for LSM-tree-based Key-Value Sto...

引用

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

作者： Xuzhen Jiang Miao Cai Baoliu Ye School of Computer and Information Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University State Key Laboratory for Novel Software Technology Nanjing University

Log Structured Merge tree (LSM-tree) is widely used in modern key-value stores due to its superior write performance. However, current LSM-tree-based key-value stores suffer from two performance issues: (1) write stall caused by speed gap between fast DRAM and slow storage devices; (2) write amplification incurred by existing LSM-tree compaction. This paper proposes NV-Cache, a write-optimized non-volatile cache for LSM-tree-based key-value stores. We design a split LSM-tree over a hybrid storage hierarchy consisting of fast Non-Volatile Memory (NVM) and slow solid state drive (SSD). It promotes frequently-accessed, high LSM-tree levels onto fast NVM and offloads cold, large LSM-tree levels into the slow storage device. Further, we propose a range of techniques, including unsorted LSM-tree node layout, lightweight MemTable flush, write-optimal list compaction, and LRU-based NV-Cache eviction, to extensively optimize the write path. NV-Cache closes the performance gap between fast DRAM and slow storage devices to prevent the write stall and reduce write amplification. We implement NV-Cache based on Google LevelDB and conduct a series of experiments using db_bench and YCSB workloads. Experiment results suggest that NV-Cache effectively prevents write stall, achieves 2.3× write reduction, and performs 54% better than LeveIDB., novelSM., and MatrixKV.

关键词： Performance evaluation Nonvolatile memory Solid state drives Layout Random access memory Internet Compaction

来源：评论

学校读者我要写书评

暂无评论

Diff-Reg v2: Diffusion-Based Matching Matrix Estimation for Image Matching and 3D Registration

arXiv

引用

arXiv 2025年

作者： Wu, Qianliang Jiang, Haobo Ding, Yaqing Luo, Lei Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China School of Computer Science and Engineering Nanjing University of Science and Technology China Nanyang Technological University Singapore Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China

Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registration. However, these tasks are often complicated by challenges such as scale inconsistencies, symmetry, and large deformations, which can lead to ambiguous matches. Previous feature-based and correspondence-based methods typically rely on geometric or semantic features to generate or polish initial potential correspondences. Some methods typically leverage specific geometric priors, such as topological preservation, to devise diverse and innovative strategies tailored to a given enhancement goal, which cannot be exhaustively enumerated. Additionally, many previous approaches rely on a single-step prediction head, which can struggle with local minima in complex matching scenarios. To address these challenges, we introduce an innovative paradigm that leverages a diffusion model in matrix space for robust matching matrix estimation. Our model treats correspondence estimation as a denoising diffusion process in the matching matrix space, gradually refining the intermediate matching matrix to the optimal one. Specifically, we apply the diffusion model in the doubly stochastic matrix space for 3D-3D and 2D-3D registration tasks. In the 2D image registration task, we deploy the diffusion model in a matrix sub-space, where dual-softmax projection regularization is applied. For all three registration tasks, we provide adaptive matching matrix embedding implementations tailored to the specific characteristics of each task while maintaining a consistent"match-to-warp" encoding pattern. Furthermore, we adopt a lightweight design for the denoising module. In inference, once points or image features are extracted and fixed, this module performs multi-step denoising predictions through reverse sampling. Evaluations on both 2D and 3D registration tasks demonstrate the effectiveness of our approach. Copyrigh

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Laplace Distribution Noise Background Modeling for Sperm Detection in Microscopic Images 9

Heterogeneous Laplace Distribution Noise Background Modeling...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Tian, Manqing Zhao, Yang Zeng, Ni Kang, Xiaomei Pei, Jihong Yang, Xuan Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen China Shenzhen University College of Computer Science and Software Engineering Shenzhen China Huazhong University of Science and Technology Tongji Medical College Department of Reproductive Maternal and Child Health Hospital of Hubei Province Wuhan China

ISBN: (纸本)9798350317251

Semen quality assessment is a very important tool for the timely detection and treatment of infertility disorders. Many artificial intelligence methods for sperm image analysis have emerged in recent years. Sperm detection in sperm microscopy is the first step in semen quality assessment. However, the acquisition of sperm electron microscopy images can produce a variety of different background lighting situations. The performance of established methods is susceptible to changes in background illumination. Therefore, a sperm detection method with heterogeneous Laplacian distribution noise background modeling (HLDNBM) is proposed. In this paper the method uses background illumination surface fitting to eliminate the effect of illumination in a single sperm image, and realizes the segmentation of sperm head and sperm tail with different grayscale by upper and lower segmentation threshold surfaces to achieve complete sperm image segmentation and multi-target detection in a single image. This method effectively avoids the degradation of target detection performance caused by sudden changes in illumination in other background modeling methods. Moreover, this method shows strong adaptability for images with different lighting backgrounds, and is friendly to small datasets as well. The experimental results show that the accuracy and sensitivity of the algorithm for sperm detection in images with different grayscale characteristics are very promising, with high universality and robustness. © 2023 IEEE.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：