检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liu, Ji Jia, Juncheng Zhang, Hong Yun, Yuhui Wang, Leye Zhou, Yang Dai, Huaiyu Dou, Dejing Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China School of Computer Science and Technology Soochow University Collaborative Innovation Center of Novel Software Technology and Industrialization Suzhou China School of Computer Science and Technology Soochow University Suzhou China Baidu Research Beijing China Key Lab of High Confidence Software Technologies Ministry of Education Software Institute Peking University Beijing China Department of Computer Science and Software Engineering Auburn University Auburn United States Department of Electrical and Computer Engineering North Carolina State University NC United States BEDI Cloud and School of Computer Science Fudan University Beijing China

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent trade-off between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller). © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Low-Latency, Predictable, and High-Precision Networking for Cooperative Vehicle Infrastructure system

SSRN

引用

SSRN 2022年

作者： Lin, Chi Wu Yu, Chang Wang, Ning Institute of Intelligent System School of Software Dalian University of Technology Dalian China Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Computer Science & Research Rowan University GlassboroNJ United States

Traditionally, infrastructural architects and road design have independently analyzed respective subsystems' needs in customary transportation. The two's inability to cooperate has culminated in possible safety issues, lousy road congestion, and unnecessary resource utilization. Moreover, challenges concerning sensor arrangement, data collecting, wireless communications, multi-source data fusion, analytical methodologies, and the development of decision-making processes might occur when cooperative vehicle infrastructure systems are used. In recent decades, Cooperative vehicle infrastructure systems(CVIS) have been suggested to assure intelligent transportation's effectiveness, effectiveness, and durability by integrating cars and infrastructures. A cooperative vehicle infrastructure system represents a novel business structure linked to businesses like autos, semiconductors, relevant information, and road infrastructure. Informatics, machine intelligence, telecommunications, data fusion, and intelligent monitoring are all included in this domain. Recent generations of networking technologies are pushing the boundaries of what became achievable utilizing cooperative vehicle infrastructure systems. Especially cooperative vehicle infrastructure systems, such instance, factory automation, Mixed Reality, and Touchscreen Network need ultra-low delay evaluated in single-digit milliseconds and cannot accept any fluctuation. Higher financial literacy requires an increased cloudification of application scenarios that require precise service level requirements for cooperative vehicle infrastructure systems. Almost all of those apps are mission-critical and therefore can risk perhaps a data packet being interrupted. Consequently, emerging applications need network infrastructure capable of delivering high-precision and predictable levels of service and accompanying assurances bordering on predictability. Cooperative vehicle infrastructure systems will require reassessing the f

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Distributed Deutsch-Jozsa Algorithm

SSRN

引用

SSRN 2024年

作者： Li, Hao Qiu, Daowen Luo, Le Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China School of Physics and Astronomy Sun Yat-sen University Zhuhai519082 China The Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China QUDOOR Technologies Inc. Zhuhai China

Deutsch-Jozsa (DJ) problem is one of the most important problems demonstrating the power of quantum algorithm, which can be described as a Boolean function $f: \{0,1\}^n\rightarrow \{0,1\}$ with promising it is either constant or balanced, and the purpose is to determine which type it is. DJ algorithm can compute it exactly with one query. However, classical deterministic algorithm requires $2^{n-1} + 1$ queries to compute it in the worse case. Therefore, DJ algorithm is essentially faster than any possible classical deterministic algorithm for computing DJ problem. In this paper, we discover the intrinsic structure of DJ problem in distributed scenario by giving a number of equivalence characterizations between $f$ being constant (balanced) and some properties of $f$'s subfunctions. We propose three distributed DJ algorithms, which have essential acceleration compared to distributed classical deterministic DJ algorithm. In comparison to DJ algorithm, our algorithms can reduce the number of qubits for a single computing node. Furthermore, compared to distributed DJ algorithm with errors, our algorithms possess accuracy and improved scalability. © 2024, The Authors. All rights reserved.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

Reshaping the ISAC Tradeoff Under OFDM Signaling: A Probabilistic Constellation Shaping Approach

arXiv

引用

arXiv 2023年

作者： Du, Zhen Liu, Fan Xiong, Yifeng Han, Tony Xiao Eldar, Yonina C. Jin, Shi The School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China The School of Information and Electronic Engineering Beijing University of Posts and Telecommunications Beijing China Huawei Technologies Co. Ltd Shenzhen China The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot Israel National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Integrated sensing and communications is regarded as a key enabling technology in the sixth generation networks, where a unified waveform, such as orthogonal frequency division multiplexing (OFDM) signal, is adopted to facilitate both sensing and communications (S&C). However, the random communication data embedded in the OFDM signal results in severe variability in the sidelobes of its ambiguity function (AF), which leads to missed detection of weak targets and false detection of ghost targets, thereby impairing the sensing performance. Therefore, balancing between preserving communication capability (i.e., the randomness) while improving sensing performance remains a challenging task. To cope with this issue, we characterize the random AF of OFDM communication signals, and demonstrate that the AF variance is determined by the fourth-moment of the constellation amplitudes. Subsequently, we propose an optimal probabilistic constellation shaping (PCS) approach by maximizing the achievable information rate (AIR) under the fourth-moment, power and probability constraints, where the optimal input distribution may be numerically specified through a modified Blahut-Arimoto algorithm. To reduce the computational overheads, we further propose a heuristic PCS approach by actively controlling the value of the fourth-moment, without involving the communication metric in the optimization model, despite that the AIR is passively scaled with the variation of the input distribution. Numerical results show that both approaches strike a scalable performance tradeoff between S&C, where the superiority of the PCS-enabled constellations over conventional uniform constellations is also verified. Notably, the heuristic approach achieves very close performance to the optimal counterpart, at a much lower computational complexity. Copyright © 2023, The Authors. All rights reserved.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Natural Image Matting by Refining Low-resolution Alpha Mattes

引用

IEEE Transactions on Image Processing 2025年 34卷 3323-3335页

作者： Ye, Xianmin Liang, Yihui Tan, Mian Feng, Fujian Wang, Lin Huang, Han Guizhou Minzu University College of Data Science and Information Engineering Guiyang 550025 China Guizhou Minzu University Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guiyang 550025 China University of Electronic Science and Technology of China School of Computer Science Zhongshan Institute Zhongshan 528400 China South China University of Technology School of Software Engineering Guangzhou 510006 China Key Laboratory of Big Data and Intelligent Robot (SCUT) MOE of China Guangzhou 510006 China Guangdong Engineering Center for Large Model and GenAI Technology Guangzhou 510006 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun 130012 China

High-resolution natural image matting plays an important role in image editing, film-making and remote sensing due to its ability of accurately extract the foreground from a natural background. However, due to the complexity brought about by the proliferation of resolution, the existing image matting methods cannot obtain high-quality alpha mattes on high-resolution images in reasonable time. To overcome this challenge, we introduce a high-resolution image matting framework based on alpha matte refinement from low-resolution to high-resolution (HRIMF-AMR). The proposed framework transforms the complex high-resolution image matting problem into low-resolution image matting problem and high-resolution alpha matte refinement problem. While the first problem is solved by adopting an existing image matting method, the latter is addressed by applying the Detail Difference Feature Extractor (DDFE) designed as a part of our work. The DDFE extracts detail difference features from high-resolution images by measuring the image feature difference between high-resolution images and low-resolution images. The low-resolution alpha matte is refined according to the extracted detail difference feature, providing the high-resolution alpha matte. In addition, the Matte Detail Resolution Difference (MDRD) loss is introduced to train the DDFE, which imposes an additional constraint on the extraction of detail difference features with mattes. Experimental results show that integrating HRIMF-AMR significantly enhances the performance of existing matting methods on high-resolution images of Transparent-460 and Alphamatting. © 1992-2012 IEEE.

关键词： alpha matte detail detail difference feature High-resolution image matting natural image matting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based software engineering: Progress, Challenges, and Opportunities

arXiv

引用

arXiv 2024年

作者： Chen, Xiangping Hu, Xing Huang, Yuan Jiang, He Ji, Weixing Jiang, Yanjie Jiang, Yanyan Liu, Bo Liu, Hui Li, Xiaochen Lian, Xiaoli Meng, Guozhu Peng, Xin Sun, Hailong Shi, Lin Wang, Bo Wang, Chong Wang, Jiayi Wang, Tiantian Xuan, Jifeng Xia, Xin Yang, Yibiao Yang, Yixin Zhang, Li Zhou, Yuming Zhang, Lu Ministry of Education School of Computer Science Peking University Beijing100871 China School of Journalism and Communication Sun Yat-sen University Guangzhou510275 China School of Software Technology Zhejiang University Hangzhou310058 China School of Software Engineering Sun Yat-sen University Guangzhou510275 China School of Software Dalian University of Technology Dalian116024 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Information Engineering Chinese Academy of Sciences Beijing100864 China School of Computer Science Fudan University Shanghai200433 China School of Software Beihang University Beijing100191 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China School of Computer Science Wuhan University Wuhan430072 China Huawei Technologies Hangzhou China

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many papers have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However, although several surveys have provided overall pictures of the application of deep learning techniques in software engineering, they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this paper, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out the through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas, we highlight the major advances achieved by applying deep learning techniques with pointers to the available data

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs

arXiv

引用

arXiv 2025年

作者： Wang, Xiaoqin Ma, Xusen Hou, Xianxu Ding, Meidan Li, Yudong Chen, Junliang Chen, Wenting Peng, Xiaoyang Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China AIAC Xi’an Jiaotong-Liverpool University China Tsinghua University China The Hong Kong Polytechnic University Hong Kong City University of Hong Kong Hong Kong Sun Yat-sen University China

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the structure, the proposed FaceBench consists of 49,919 visual question-answering (VQA) pairs for evaluation and 23,841 pairs for fine-tuning. Moreover, we further develop a robust face perception MLLM baseline, Face-LLaVA, by training with our proposed face VQA data. Extensive experiments on various mainstream MLLMs and Face-LLaVA are conducted to test their face perception ability, with results also compared against human performance. The results reveal that, the existing MLLMs are far from satisfactory in understanding the fine-grained facial attributes, while our Face-LLaVA significantly outperforms existing open-source models with a small amount of training data and is comparable to commercial ones like GPT-4o and Gemini. The dataset will be released at https://***/CVI-SZU/FaceBench. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prediction of Fuel Consumption and Carbon Emissions in Light-Duty Vehicles using Convolutional Recurrent Imputation Network

Enhanced Prediction of Fuel Consumption and Carbon Emissions...

引用

International Conference on Computer, Electrical & Communication engineering (ICCECE)

作者： T. Lalitha Jerzy Ryszard Szymański Marta Żurek-Mortka Mithileysh Sathiyanarayanan K. R. Srilekha Computer Science School of Information Science Presidency University Bengaluru Karnataka India Department of Electrical Drives and Industrial Electronics Faculty of Transport Electrical Engineering and Computer Sciences Casimir Pulaski University of Radom Poland Europe Lukasiewicz Research Network Institute for Sustainable Technologies Kazimierza Pułaskiego Radom Poland Europe MIT Square London I M.Tech Integrated(Software Engineering) VIT University Vellore Tamilnadu India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

Fuel utilization and emission estimation are essential for assessing the consequence of materials and strict emission control measures due to the startling rate of weather changes. The world's socioeconomic issues are significantly impacted by the growing worldwide average temperature and its effects on climate change. The melting of the polar ice caps, that is a direct result of this rise, leads to a number of other problems, such as the polar animal’s death, coastal flooding, and exposure to bacteria and earliest microorganisms that are frozen in the snow and could cause many more global pandemics and invisible illnesses. In this paper, Enhanced Prediction of Fuel Consumption and Carbon Emissions in Light-Duty Vehicles using Dynamic Graph Convolutional Recurrent Imputation Network (EP-FCCE-DGCRIN) are proposed.. The effectiveness of the EP-FCCE-DGCRIN technique is compared to other existing methods. This research offers evidence-based suggestions to lessen the environmental effects of vehicles for both manufacturers and consumers depending upon the outcomes of the Descriptive Statistics analysis.

关键词： Temperature measurement Pandemics Snow Sea measurements Carbon dioxide Imputation Fuels Vehicle dynamics Socioeconomics Meteorology

来源：评论

学校读者我要写书评

暂无评论

A new quantum machine learning algorithm: split hidden quantum Markov model inspired by quantum conditional master equation

arXiv

引用

arXiv 2023年

作者： Li, Xiao-Yu Zhu, Qin-Sheng Hu, Yong Wu, Hao Yang, Guo-Wu Yu, Lian-Hui Chen, Geng School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China School of Physics University of Electronic Science and Technology of China Chengdu610054 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610103 China Institute of Electronics and Information Industry Technology of Kash Kash 844000 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610054 China

The Hidden Quantum Markov Model (HQMM) has significant potential for analyzing time-series data and studying stochastic processes in the quantum domain as an upgrading option with potential advantages over classical Markov models. In this paper, we introduced the split HQMM (SHQMM) for implementing the hidden quantum Markov process, utilizing the conditional master equation with a fine balance condition to demonstrate the interconnections among the internal states of the quantum system. The experimental results suggest that our model outperforms previous models in terms of scope of applications and robustness. Additionally, we establish a new learning algorithm to solve parameters in HQMM by relating the quantum conditional master equation to the HQMM. Finally, our study provides clear evidence that the quantum transport system can be considered a physical representation of HQMM. The SHQMM with accompanying algorithms present a novel method to analyze quantum systems and time series grounded in physical implementation. © 2023, CC BY-NC-SA.

关键词： Stochastic systems

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：