检索结果-内蒙古大学图书馆

MFF-YOLO: An Improved YOLO Algorithm Based on Multi-Scale Semantic Feature Fusion

Tsinghua Science and Technology 2025年第5期30卷 2097-2113页

作者： Junsan Zhang Chenyang Xu Shigen Shen Jie Zhu Peiying Zhang Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao China School of Information Engineering Huzhou University Huzhou China Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China National Research Center for Information Science and Technology Tsinghua University Beijing China

The YOLOv5 algorithm is widely used in edge computing systems for object detection. However, the limited computing resources of embedded devices and the large model size of existing deep learning based methods increase the difficulty of real-time object detection on edge devices. To address this issue, we propose a smaller, less computationally intensive, and more accurate algorithm for object detection. Multi-scale Feature Fusion-YOLO (MFF-YOLO) is built on top of the YOLOv5s framework, but it contains substantial improvements to YOLOv5s. First, we design the MFF module to improve the feature propagation path in the feature pyramid, which further integrates the semantic information from different paths of feature layers. Then, a large convolution-kernel module is used in the bottleneck. The structure enlarges the receptive field and preserves shallow semantic information, which overcomes the performance limitation arising from uneven propagation in Feature Pyramid Networks (FPN). In addition, a multi-branch downsampling method based on depthwise separable convolutions and a bottleneck structure with deformable convolutions are designed to reduce the complexity of the backbone network and minimize the real-time performance loss caused by the increased model complexity. The experimental results on PASCAL VOC and MS COCO datasets show that, compared with YOLOv5s, MFF-YOLO reduces the number of parameters by 7% and the number of FLoating point Operations Per second (FLOPs) by 11.8%. The mAP@0.5 has improved by 3.7% and 5.5%, and the mAP@0.5:0.95 has improved by 6.5% and 6.2%, respetively. Furthermore, compared with YOLOv7-tiny, PP-YOLO-tiny, and other mainstream methods, MFF-YOLO has achieved better results on multiple indicators.

关键词： YOLO Deformable models Accuracy Computational modeling Image edge detection Semantics Neural networks Feature extraction Real-time systems Edge computing

来源：评论

学校读者我要写书评

暂无评论

ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement

arXiv

引用

arXiv 2025年

作者： Guo, Xuejian Tian, Zhiqiang Wang, Yuehang Li, Siqi Jiang, Yu Du, Shaoyi Gao, Yue the School of Software Engineering Xi’an Jiaotong University Xi’an710049 China the College of Computer Science and Technology Jilin University Changchun130012 China the National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China BNRist THUIBCS KLISS BLBCI School of Software Tsinghua University Beijing100084 China

Low-light image enhancement aims to restore the under-exposure image captured in dark scenarios. Under such scenarios, traditional frame-based cameras may fail to capture the structure and color information due to the exposure time limitation. Event cameras are bio-inspired vision sensors that respond to pixel-wise brightness changes asynchronously. Event cameras’ high dynamic range is pivotal for visual perception in extreme low-light scenarios, surpassing traditional cameras and enabling applications in challenging dark environments. In this paper, inspired by the success of the retinex theory for traditional frame-based low-light image restoration, we introduce the first methods that combine the retinex theory with event cameras and propose a novel retinex-based low-light image restoration framework named ERetinex. Among our contributions, the first is developing a new approach that leverages the high temporal resolution data from event cameras with traditional image information to estimate scene illumination accurately. This method outperforms traditional image-only techniques, especially in low-light environments, by providing more precise lighting information. Additionally, we propose an effective fusion strategy that combines the high dynamic range data from event cameras with the color information of traditional images to enhance image quality. Through this fusion, we can generate clearer and more detail-rich images, maintaining the integrity of visual information even under extreme lighting conditions. The experimental results indicate that our proposed method outperforms state-of-the-art (SOTA) methods, achieving a gain of 1.0613 dB in PSNR while reducing FLOPS by 84.28%. The code is available at https://***/lodew920/ERetinex. © 2025, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of IRS-Assisted Multi-Cell Data and Energy Integrated Networks

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Bingxin Yang, Kun Wang, Kezhi Zhang, Guopeng Nanjing University State Key Laboratory of Novel Software Technology Nanjing 210008 China Nanjing University School of Intelligent Software and Engineering Suzhou Campus Suzhou 215163 China Brunel University London Department of Computer Science Middlesex Uxbridge UB8 3PH United Kingdom China University of Mining and Technology School of Computer Science and Technology Xuzhou 221116 China

Intelligent reflecting surface (IRS) can significantly enhance the performance of data and energy integrated networks (DEIN) by adjusting its amplitude and/or phase. However, there is a lack of comprehensive performance analysis model for realistic DEIN where multiple cells exist rather than only one cell as assumed by most existing work. In this paper, we consider an IRS-assisted multi-cell DEIN. Specifically, in the downlink wireless energy transfer (WET) stage, the hybrid access point (HAP) in each cell broadcasts radio frequency (RF) energy signals to edge user equipments (UEs). Subsequently, during the uplink wireless information transfer (WIT) stage, the edge UEs employ the harvested energy to send their information to the HAP. We first represent the statistical characteristics of the signal-to-interference-plus-noise ratio (SINR) at the edge UE. Then, we derive the closed-form expressions for outage probability, ergodic rate and average symbol error probability of the edge UE in the typical cell. To gain more insights, we obtain the minimum required number of reflection elements and a sub-optimal solution for time allocation coefficients. Finally, extensive numerical results are provided to validate the correctness of the theoretical results. © 2002-2012 IEEE.

关键词： data and energy integrated network (DEIN) Intelligent reflecting surface (IRS) multi-cell performance analysis wireless energy transfer (WET)

来源：评论

学校读者我要写书评

暂无评论

REPRESENTATION AND AUTOMATED TRANSFORMATION OF GEOMETRIC STATEMENTS

引用

Journal of Systems Science & Complexity 2014年第2期27卷 382-412页

作者： CHEN Xiaoyu State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University

The emergence of a large quantity of digital resources in geometry, various geometric automated theorem proving systems, and kinds of dynamic geometry software systems has made geometric computation, reasoning, drawing, and knowledge management dynamic, automatic or interactive on computer. Integration of electronic contents and different systems is desired to enhance their accessibility and exploitability. This paper proposes an equivalent transformation framework for manipulating geometric statements available in the literature by using geometry software systems. Such a framework works based on a newly designed geometry description language(GDL), in which geometric statements can be represented naturally and easily. The author discusses and presents key procedures of automatically transforming GDL statements into target system-native representations for *** author also demonstrates the framework by illustrating equivalent transformation processes and interfaces for compiling the transformation results into executable formats that can be interpreted by the target geometry software systems for automated theorem proving and dynamic diagram drawing.

关键词： Automated diagram drawing equivalent transformation formalized geometric statements geometric automated theorem proving.

来源：评论

学校读者我要写书评

暂无评论

Accelerating MUS enumeration by inconsistency graph partitioning

引用

Science China(Information Sciences) 2019年第11期62卷 70-80页

作者： Jie LUO Shaofan LIU State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University

The problem of finding minimal unsatisfiable subsets(MUSes) has been studied frequently because of its theoretical importance and wide range of applications in domains such as electronic design automation, software, and integrated circuit verification. In this paper, a method for accelerating the enumeration of MUSes based on inconsistency graph partitioning is proposed. First, an inconsistency graph of a set of clauses is constructed by extracting the inconsistency relations between literals of different clauses. In this paper, we show that by partitioning the inconsistency graph into small connected components through a vertex cut, the enumeration of MUSes in different components becomes independent and it is possible to compute them separately. Moreover, the MUSes of the original clause set can be constructed by merging the unit clauses in the MUSes of these connected components back into the clauses in the vertex cut. Experiments show that by integrating the acceleration method into the MARCO MUSes enumerator, there is a 2–3 times improvement in the average runtime of solved instances for randomly generated benchmarks. By integrating the acceleration method into itself as an MUS enumerator, there is another 3–4 times improvement when compared with the accelerated MARCO.

关键词： minimal unsatisfiable subsets inconsistency graph graph partition SAT UNSAT

来源：评论

学校读者我要写书评

暂无评论

A CNN-Based Model for Yield Prediction in MEMS Resonator Manufacturing

A CNN-Based Model for Yield Prediction in MEMS Resonator Man...

引用

IEEE/SEMI Conference and Workshop on Advanced Semiconductor Manufacturing

作者： Yikang Ding Bo Wen Qi Wang Chong Chen Xiangshu Lei Yufeng Jin Wei Wang School of Electronic and Computer Engineering Peking University Shenzhen China School of Integrated Circuits Peking University Beijing China School of Software & Microelectronics Peking University Beijing China Faculty of Information and Communication Engineering Dalian University of Technology Dalian China School of Electronic and Computer Engineering School of Integrated Circuits Peking University Beijing China School of Integrated Circuits National Key Laboratory of Advanced Micro and Nano Manufacture Technology Peking University Beijing China

ISBN: (数字)9798331531850

ISBN: (纸本)9798331531867

This work presents a novel method for predicting the yield of Micro-electromechanical Systems (MEMS) resonators by using Convolutional Neural Networks (CNNs) to extract morphological features from cross-sections images of MEMS resonators’ beams produced by Deep Reactive-Ion Etching (DRIE). By establishing a model that maps the relationships between the MEMS resonators’ operating frequency and the morphological variations in beams induced by process deviations, this method can predict the operating frequency more than 10 3 times faster than Finite Element Analysis (FEA) simulation, achieving over 96.7% accuracy, advancing the standardization of MEMS resonators manufacturing flow.

关键词： Micromechanical devices Microelectromechanical systems Time-frequency analysis Resonant frequency Standardization Predictive models Feature extraction Manufacturing Convolutional neural networks Resonators

来源：评论

学校读者我要写书评

暂无评论

Solving All-SAT Problems by P Systems

引用

Chinese Journal of Electronics 2015年第4期24卷 744-749页

作者： GUO Ping JI Jinfang CHEN Haizhu LIU Ran College of Computer Science Chongqing University Chongqing Key Laboratory of Software Theory & Technology Department of Software Engineering Chongqing College of Electronic Engineering

The satisfiability problem(SAT) is a well known NP-complete problem. Obtaining All of the truth assignments of SAT is called All-SAT and it has numerous applications in artificial intelligence and computer theories. Many algorithms about SAT have been built, but how to solve All-SAT is still difficult. P system is a new distributed and parallel computation model. We use membrane division, which is frequently investigated to obtain an exponential working space in a linear time, to design a family of P systems to solve All-SAT in polynomial *** work provides a new and effective solution to All-SAT in a distributed and parallel manner.

关键词： All solutions for Satisfiability problem(All-SAT) Satisfiability problem(SAT problem) Conjunctive normal form(CNF) P system Memb

来源：评论

学校读者我要写书评

暂无评论

A Linear-Time Solution for All-SAT Problem Based on P System

引用

Chinese Journal of Electronics 2018年第2期27卷 367-373页

作者： GUO Ping ZHU Jian CHEN Haizhu YANG Ruilong College of Computer Science Chongqing University Chongqing Key Laboratory of Software Theory and Technology Department of Software Engineering Chongqing College of Electronic Engineering

P system is a new kind of distributed parallel computing model, and its many variants are used to solve NP problems. All-SAT problem is a well-known NPhard problem and it has been widely applied in the fields of pro ject selection problem, capital budgeting problem and so on. In this paper, we present a family of P systems to solve All-SAT problem in a linear time based on membrane division and give an instance to illustrate the feasibility and effectiveness of our designed P systems.

关键词： Membrane computing Cell-like P systems Boolean Satisfiability problem(SAT problem) Find All solutions of SAT(All-SAT) problem

来源：评论

学校读者我要写书评

暂无评论

A Family of P Systems for Solving Linear Equations

引用

Chinese Journal of Electronics 2017年第4期26卷 667-674页

作者： GUO Ping WEI Lijiao CHEN Haizhu LIU Ran College of Computer Science Chongqing University Chongqing Key Laboratory of Software Theory and Technology Department of Software Engineering Chongqing College of Electronic Engineering

Solving linear equations is one of the fundamental problems in numerical calculation and has a wide application in many science and engineering fields. We present a family of P systems to solve linear equations in which the coefficients are real numbers. An instance is given to illustrate the feasibility and effectiveness of our designed P systems. Our work contributes to make P systems to solve more complicated computation problems effectively.

关键词： Membrane computing Cell-like P systems Fraction arithmetic operation Numerical calculation P systems

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xin Li Feng Xu Feifei Tao Yao Tong Xin Lyu Jianyi Zhong André Kaup College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Chair of Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study.

关键词： Semantic segmentation Frequency-domain analysis Urban planning Semantics Speech enhancement Signal processing Transformers Sensors Remote sensing Standards

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：