检索结果-内蒙古大学图书馆

DPNet: Dynamic Pooling Network for Accurate and Efficient Size-Aware Tiny Object Detection

IEEE Internet of Things Journal 2025年

作者： Gong, Luqi Chen, Haotian Chen, Yikun Yao, Tianliang Li, Chao Zhao, Shuai Han, Guangjie Beijing University of Posts and Telecommunications School of Computer Science Beijing China Zhejiang Lab Research Center for Space Computing System Hangzhou China Southwest Jiaotong University SWJTU-LEEDS Joint School Chengdu China LTD Guangdong Zhiyun City construction Technology Co Zhuhai China Tongji University College of Electronic and Information Engineering Department of Control Science and Engineering Shanghai China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed down-sampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware down-sampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection *** code will be made publicly available. © 2014 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DPNet: Dynamic Pooling Network for Tiny Object Detection

arXiv

引用

arXiv 2025年

作者： Gong, Luqi Chen, Haotian Chen, Yikun Yao, Tianliang Li, Chao Zhao, Shuai Han, Guangjie School of Computer Science Beijing University of Posts and Telecommunications Beijing China Research Center for Space Computing System Zhejiang Lab Hangzhou China SWJTU-LEEDS Joint School Southwest Jiaotong University Chengdu China Guangdong Zhiyun City construction Technology Co. LTD Zhuhai China Department of Control Science and Engineering College of Electronic and Information Engineering Tongji University Shanghai China Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education Hohai University China

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed downsampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware downsampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection *** code will be made publicly available. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

CAMAL: Context-aware multi-scale attention framework for lightweight visual place recognition

arXiv

引用

arXiv 2019年

作者： Khaliq, Ahmad Ehsan, Shoaib Milford, Michael McDonald-Maier, Klaus Embedded and Intelligent System Lab in School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom Australian Centre for Robotic Vision and School of Electrical Engineering and Computer Science Queensland University of Technology Brisbane Australia

In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art performances for Visual Place Recognition (VPR). Their prestigious generalization power has played a vital role in identifying persistent image regions under changing conditions and viewpoints. However, against the computation intensive D-CNNs based VPR algorithms, lightweight VPR techniques are preferred for resource-constraints mobile robots. This paper presents a lightweight CNN-based VPR technique that captures multilayer context-aware attentions robust under changing environment and viewpoints. Evaluation of challenging benchmark datasets reveals better performance at low memory and resources utilization over state-of-the-art contemporary VPR methodologies. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Transportation,germs,culture:a dynamic graph model of COVID-19 outbreak

引用

Quantitative Biology 2020年第3期8卷 238-244页

作者： Xiaofei Yang Tun Xu Peng Jia Han Xia Li Guo Lei Zhang Kai Ye School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049China MOE Key Lab for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049China School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049China Hugobiotech Co. Ltd.Beijing 102600China The School of Life Science and Technology Xi'an Jiaotong UniversityXi'an 710049China China-Australia Joint Research Center for Infectious Diseases School of Public HealthXi'an Jiaotong University Health Science CenterXi'an 710061China Melbourne Sexual Health Centre Alfred HealthMelbourneVIC 3004Australia Central Clinical School Faculty of MedicineNursing and Health SciencesMonash UniversityMelbourneVIC 3004Australia Department of Epidemiology and Biostatistics College of Public HealthZhengzhou UniversityZhengzhou 450001China Genome Institute the First Affiliated Hospital of Xi'an Jiaotong UniversityXi'an 710061China

Backgrounds Various models have been applied to predict the trend of the epidemic since the outbreak of ***:In this study,we designed a dynamic graph model,not for precisely predicting the number of infected cases,but for a glance of the dynamics under a public epidemic emergency situation and of different contributing factors・Results^We demonstrated the impact of asymptomatic transmission in this outbreak and showed the effectiveness of city lockdown to halt virus spread within a *** further illustrated that sudden emergence of a large number of cases could overwhelm the city medical system,and external medical aids are critical to not only containing the further spread of the virus but also reducing *** Our model simulation showed that highly populated modern cities are particularly vulnerable and lessons learned in China could facilitate other countries to plan the proactive and decisive actions・We shall pay close attention to the asymptomatic transmission being suggested by rapidly accumulating evidence as dramatic changes in quarantine protocol are required to contain SARS・CoV・2 from spreading globally.

关键词： dynamic graph model transportation COVID-19 SARS-CoV-2

来源：评论

学校读者我要写书评

暂无评论

Resistive memory-based zero-shot liquid state machine for multimodal event data learning

arXiv

引用

arXiv 2023年

作者： Lin, Ning Wang, Shaocong Li, Yi Wang, Bo Shi, Shuhui He, Yangu Zhang, Woyu Yu, Yifei Zhang, Yue Zhang, Xinyuan Wong, Kwunhang Wang, Songqi Chen, Xiaoming Jiang, Hao Zhang, Xumeng Lin, Peng Xu, Xiaoxin Qi, Xiaojuan Wang, Zhongrui Shang, Dashan Liu, Qi Liu, Ming Department of Electrical and Electronic Engineering the University of Hong Kong Hong Kong Key Lab of Fabrication Technologies for Integrated Circuits and Key Laoratory of Microelectronic Devices and Integrated Technology Institute of Microelectronics the Chinese Academy of Sciences Beijing100029 China The School of Microelectronics Southern University of Science and Technology Shenzhen518055 China ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong University of Chinese Academy of Sciences Beijing100049 China Frontier Institute of Chip and System Fudan University Shanghai200433 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

The human brain is a complex spiking neural network (SNN), capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal propagation. However, replicating the human brain in neuromorphic hardware presents both hardware and software challenges. Hardware limitations, such as the slowdown of Moore’s law and Von Neumann bottleneck, hinder the efficiency of digital computers. Additionally, SNNs are characterized by their software training complexities. To this end, we propose a hardware-software co-design on a 40 nm 256 Kb in-memory computing macro that physically integrates a fixed and random liquid state machine (LSM) SNN encoder with trainable artificial neural network (ANN) projections. We showcase the zero-shot LSM-based learning of multimodal events on the N-MNIST and N-TIDIGITS datasets, including visual and audio data association, as well as neural and visual data alignment for brain-machine interfaces. Our co-design achieves classification accuracy comparable to fully optimized software models, resulting in a 152.83 and 393.07-fold reduction in training costs compared to SOTA contrastive language-image pre-training (CLIP) and Prototypical networks, and a 23.34 and 160-fold improvement in energy efficiency compared to cutting-edge digital hardware, respectively. These proof-of-principle prototypes demonstrate zero-shot multimodal events learning capability for emerging efficient and compact neuromorphic hardware. © 2023, CC BY-NC-SA.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Large circuit models: opportunities and challenges

引用

science CHINA Information sciences 2024年第11期67卷 1-1页

作者： Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan SHI Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y. YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU Huawei Noah's Ark Lab Hong Kong 999077 China School of Integrated Circuits Peking University Beijing 100871 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo 315211 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong 999077 China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong 999077 China School of Integrated Circuits Southeast University Nanjing 210096 China Huawei HiSilicon Shenzhen 518129 China Peng Cheng Laboratory Shenzhen 518052 China School of Computer Science Peking University Beijing 100871 China School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University Shanghai 200433 China School of Artificial Intelligence Shanghai Jiao Tong University Shanghai 200240 China

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Multidimensional Resource Management for Energy Harvesting Cognitive NOMA Communications

arXiv

引用

arXiv 2021年

作者： Shi, Zhaoyuan Yang, Helin Xie, Xianzhong Lu, Huabing Cai, Jun Ding, Zhiguo School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing China Chongqing Key Lab of Computer networks and Communication Technology Chongqing University of Posts and Telecommunications Chongqing China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada Department of Electrical Engineering Princeton University PrincetonNJ08544 United States School of Electrical and Electronic Engineering University of Manchester Manchester United Kingdom

The combination of energy harvesting (EH), cognitive radio (CR), and non-orthogonal multiple access (NOMA) is a promising solution to improve energy efficiency and spectral efficiency of the upcoming beyond fifth generation network (B5G), especially for support the wireless sensor communications in Internet of things (IoT) system. However, how to realize intelligent frequency, time, and energy resource allocation to support better performances is an important problem to be solved. In this paper, we study joint spectrum, energy, and time resource management for the EH-CR-NOMA IoT systems. Our goal is to minimize the number of data packets losses for all secondary sensing users (SSU), while satisfying the constraints on the maximum charging battery capacity, maximum transmitting power, maximum buffer capacity, and minimum data rate of primary users (PU) and SSUs. Due to the nonconvexity of this optimization problem and the stochastic nature of the wireless environment, we propose a distributed multidimensional resource management algorithm based on deep reinforcement learning (DRL). Considering the continuity of the resources to be managed, the deep deterministic policy gradient (DDPG) algorithm is adopted, based on which each agent (SSU) can manage its own multidimensional resources without collaboration. In addition, a simplified but practical action adjuster (AA) is introduced for improving the training efficiency and battery performance protection. The provided results show that the convergence speed of the proposed algorithm is about 4 times faster than that of DDPG, and the average number of packet losses (ANPL) is about 8 times lower than that of the greedy algorithm. Copyright © 2021, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Scanning Acoustic Microscopy for Quantifying Two-phase Transfer in Operando Alkaline Water Electrolyzer

arXiv

引用

arXiv 2024年

作者： Dou, Zehua Rox, Hannes Ramos, Zyzi Baumann, Robert Ravishankar, Rachappa Czurratis, Peter Yang, Xuegeng Lasagni, Andrés Fabian Eckert, Kerstin Czarske, Juergen Weik, David Faculty of Electrical and Computer Engineering Laboratory of Measurement and Sensor System Technique Technische Universität Dresden Helmholtzstraße 18 Dresden01069 Germany Institute of Fluid Dynamics Helmholtz-Zentrum Dresden-Rossendorf Bautzner Landstraße 400 Dresden01328 Germany PVA TePla Analytical Systems GmbH Deutschordenstraße 38 Westhausen73463 Germany Institute of Manufacturing Science and Engineering Technische Universität Dresden George-Baehr-Straße 3c Dresden01069 Germany Fraunhofer Institute for Material and Beam Technology IWS Winterbergstraße 28 Dresden01277 Germany Institute of Process Engineering and Environmental Technology Technische Universität Dresden Helmholtzstraße 14 Dresden01069 Germany Hydrogen Lab School of Engineering Technische Universität Dresden Helmholtzstraße 14 Dresden01062 Germany Institute for Emerging Electronic Technologies Leibniz Institute for Solid State and Materials Research Dresden Helmholtzstraße 20 Dresden01069 Germany

Improved understandings of two-phase transport in electrochemical gas-evolving systems are increasingly demanded, while high-performance imaging techniques using simplified instrumentations are not readily available. This work presents volumetric scanning acoustic microscopy (SAM) imaging for quantifying the dynamics of gas bubbles and electrolyte in porous Nickel electrodes with different wettability and structures during alkaline water electrolysis (AWE). We realize high-resolution 3D imaging at 10's µm level using high frequency spherically focused ultrasound. The high resolution allowed us to clearly visualize the spatial distributions of produced bubbles in the porous electrodes over time. Moreover, we are able to quantify the residual gas volume in an electrode and its coverage due to bubble evolution, which dominate its transport overpotential. Taking these advantages, we elucidate the impacts of electrodes' wettability and structures on their electrolysis performance, on a regular laboratory base. The obtained knowledge provides us important optimization guidelines of AWE designs and operating schemes. Copyright © 2024, The Authors. All rights reserved.

关键词： Mass transfer

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Domestic Appliances Scheduling in Community Microgrids

Blockchain Based Domestic Appliances Scheduling in Community...

引用

2019 IEEE PES Innovative Smart Grid Technologies Asia, ISGT 2019

作者： Afzal, M. Umer, Khalid Amin, Waqas Naeem, M. Cai, Dongshang Zhenyuan, Zhang Huang, Qi Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu611731 China Department of Electrical and Computer Engineering COMSATS University Islamabad Wah Campus Pakistan

ISBN: (纸本)9781728135205

This paper proposes an optimization model for community microgrid. The proposed scheme performs the scheduling of domestic appliances in a community microgrid using renewable energy resources. The objective of the scheme is to minimize the total operating cost in the whole community. The optimization problem is solved using the branch and bound algorithm. Blockchain (BC) technology is introduced for secure implementation of the proposed approach. Machine to machine interaction is facilitated using BC technology. The transaction information/ data is stored in the distributed shared ledger. The smart contract is used to automatically trigger the flow of electricity and the movement of funds once the necessary conditions are met. © 2019 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Network Pruning Method for Remote Sensing Image Scene Classification

A Network Pruning Method for Remote Sensing Image Scene Clas...

引用

2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019

作者： Qi, Baogui Chen, He Zhuang, Yin Liu, Shaorong Chen, Liang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing100081 China School of Electronic Engineering and Computer Science Peking University Beijing100087 China Beijing Institute of Spacecraft System Engineering Beijing100094 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (纸本)9781728123455

Deep convolutional neural networks have been widely used to improve remote sensing image scene classification performance. However, most of these networks include many parameters and need many computational resources. Which hinders the applications of these networks when facing the satellite, plane or other mobile platforms. In this paper, we introduce a network pruning framework which can reduce the size of the network model and maintain the classification accuracy. In this framework, we train the pruned model using both the original unpruned model's output and training dataset. Which can learn more information than retrain using dataset only. In our experiments, we evaluate our method for remote sensing scene classification on NWPU-RESISC45 dataset. The results demonstrate that our method was effective and maintained the model classification accuracy. © 2019 IEEE.

关键词： Remote sensing

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：