检索结果-内蒙古大学图书馆

LOGCAN++: Adaptive Local-Global Class-Aware Network for Semantic Segmentation of Remote Sensing Images

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Ma, Xiaowen Lian, Rongrong Wu, Zhenkai Guo, Hongbo Yang, Fan Ma, Mengting Wu, Sensen Du, Zhenhong Zhang, Wei Song, Siyang Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200030 China Zhejiang University School of Computer Science and Technology Hangzhou310027 China Zhejiang University School of Earth Sciences Hangzhou310027 China Zhejiang University School of Software Technology Hangzhou310027 China Zhejiang University Innovation Center of Yangtze River Delta Zhejiang Jiaxing314103 China University of Exeter HUBG Laboratory Department of Computer Science ExeterEX4 4PY United Kingdom

Remote sensing images are usually characterized by complex backgrounds, scale and orientation variations, and large intraclass variance. General semantic segmentation methods usually fail to fully investigate the above issues, and thus their performances on remote sensing image segmentation are limited. In this article, we propose our LOGCAN++, a semantic segmentation model customized for remote sensing images, which is made up of a global class-aware (GCA) module and several local class-aware (LCA) modules. The GCA module captures global representations for class-level context modeling to reduce the interference of background noise. The LCA module generates local class representations as intermediate perceptual elements to indirectly associate pixels with the global class representations, targeting dealing with the large intraclass variance problem. In particular, we introduce affine transformations in the LCA module for adaptive extraction of local class representations to effectively tolerate scale and orientation variations in remote sensing images. Extensive experiments on three benchmark datasets show that our LOGCAN++ outperforms current mainstream general and remote sensing semantic segmentation methods and achieves a better trade-off between speed and accuracy. © 1980-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Automatic Search for Photoacoustic Marker Using Automated Transrectal Ultrasound

arXiv

引用

arXiv 2023年

作者： Wu, Zijian Moradi, Hamid Yang, Shuojue Song, Hyunwoo Boctor, Emad M. Salcudean, Septimiu E. Johns Hopkins University Laboratory for Computational Sensing and Robotics BaltimoreMD United States University of British Columbia Dept. of Electrical and Computer Engineering VancouverBC Canada University of Texas at Austin Walker Department of Mechanical Engineering AustinTX United States Johns Hopkins University Dept. of Computer Science BaltimoreMD United States

Real-time transrectal ultrasound (TRUS) image guidance during robot-assisted laparoscopic radical prostatectomy has the potential to enhance surgery outcomes. Whether conventional or photoacoustic TRUS is used, the robotic system and the TRUS must be registered to each other. Accurate registration can be performed using photoacoustic (PA markers). However, this requires a manual search by an assistant [19]. This paper introduces the first automatic search for PA markers using a transrectal ultrasound robot. This effectively reduces the challenges associated with the da Vinci-TRUS registration. This paper investigated the performance of three search algorithms in simulation and experiment: Weighted Average (WA), Golden Section Search (GSS), and Ternary Search (TS). For validation, a surgical prostate scenario was mimicked and various ex vivo tissues were tested. As a result, the WA algorithm can achieve 0.53o ± 0.30o average error after 9 data acquisitions, while the TS and GSS algorithm can achieve 0.29° ± 0.31° and 0.48o ± 0.32o average errors after 28 data acquisitions. © 2023, CC BY.

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Regulating Covert Communication Capacity with Full-Duplex Receiver Against Location-Uncertain Eavesdropper

Regulating Covert Communication Capacity with Full-Duplex Re...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Rui Xu Gaolei Li Yuchen Liu Yue Zhao Jiawen Kang Jianhua Li School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science North Carolina State University Raleigh USA State Key Laboratory of Integrated Services Networks Xidian University Xi'an China School of Automation Guangdong University of Technology China

ISBN: (数字)9798350370997

ISBN: (纸本)9798350371000

Covert communication enforces the transmitted signal to be indistinguishable from other signals under wireless environment, making it difficult for an eavesdropper to detect and intercept the message. The most common approach within covert systems is the augmentation of artificial noise (AN), ensuring reliable transmission. However, this strategy becomes problematic when the eavesdropper's position is uncertain, as continuous amplification of interference power can precipitate a substantial decline in covert communication capacity. In this paper, we investigate the covert communication between legitimate transmitter (i.e., Alice) and full duplex receiver (i.e., Bob) in the presence of the location uncertainties of the eavesdropper (i.e., Willie). We first derive the sufficient condition for achieving covert communication through robustness analysis. Then, we derive the effective throughput to measure the covert communication capacity. Afterward, by using joint optimization technology, the optimal AN power of Bob and the number of antennas for Alice are jointly designed to maximize the effective throughput subject to a covertness constraint. Theoretical analysis indicates that reducing the AN power while increasing the number of antennas helps to improve the system capacity, the effective throughput between Alice and Bob is inversely proportional to the distance between them. Finally, the validity of our analytical approach is corroborated by simulation results.

关键词： Wireless communication Sufficient conditions Uncertainty Simulation Transmitting antennas Receivers Full-duplex system

来源：评论

学校读者我要写书评

暂无评论

MCDAL: Maximum Classifier Discrepancy for Active Learning

arXiv

引用

arXiv 2021年

作者： Cho, Jae Won Kim, Dong-Jin Jung, Yunjae Kweon, In So The Department of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of The Electrical Engineering and Computer Science Department University of California BerkeleyCA United States

Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition;however, GAN is usually known to suffer from instability and sensitivity to hyper-parameters. In contrast to these methods, we propose in this paper a novel active learning framework that we call Maximum Classifier Discrepancy for Active Learning (MCDAL) which takes the prediction discrepancies between multiple classifiers. In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them. Intuitively, the discrepancies in the auxiliary classification layers' predictions indicate the uncertainty in the prediction. In this regard, we propose a novel method to leverage the classifier discrepancies for the acquisition function for active learning. We also provide an interpretation of our idea in relation to existing GAN based active learning methods and domain adaptation frameworks. Moreover, we empirically demonstrate the utility of our approach where the performance of our approach exceeds the state-of-the-art methods on several image classification and semantic segmentation datasets in active learning setups. © 2021, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

HTCC SIW-Fed Broadband High-Gain Phased Array Antenna with Soft Surface Structure

HTCC SIW-Fed Broadband High-Gain Phased Array Antenna with S...

引用

IEEE MTT-S International Microwave Workshop Series on advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Guo Yu Yafei Wu Yuhan Fan Zhongqian Niu Fan Xiong Xu Jie Cheng Wang Bo Zhang School of Photovoltaic Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing Institute of Microelectronics Industry Technology UESTC Chongqing China Faculty of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Electrical and Computer Engineering National University of Singapore Singapore National University of Defense Technology Changsha China Key Laboratory of Satellite Navigation Technology Changsha China

ISBN: (数字)9798331520717

ISBN: (纸本)9798331520724

Proposes a high-gain phased array antenna operating in mmW band based on the HTCC process. The array consists of a $1 \times 4$ antenna array with a dipole antenna fed by a substrate-integrated waveguide (SIW) as the unit. Improve antenna bandwidth by slotting the end of the SIW for impedance matching. Soft surface structures are introduced around the radiating structure of the antenna to suppress the surface wave effect, so that the antenna obtains a gain enhancement of 3.6 dBi, and finally the maximum gain of this antenna is 9.5 dBi. Simulation results show that the phased array antenna is capable of achieving a scanning range of ± 50° within the impedance bandwidth of 24.44 GHz to 30.22 GHz (with a relative bandwidth of 21.1%), and the maximum gain loss at the scanning angle of the antenna is less than 2 dBi.

关键词： Phased arrays Wireless communication Slot antennas Dipole antennas Impedance matching Bandwidth Surface structures Microwave antenna arrays Broadband antennas Substrates

来源：评论

学校读者我要写书评

暂无评论

advanced Deep Learning Models for Groundwater Contaminant Dynamics at the Savannah River Site

Advanced Deep Learning Models for Groundwater Contaminant Dy...

引用

Future Machine Learning and Data science (FMLDS), IEEE International Conference on

作者： Jayesh Soni Himanshu Upadhyay Haruko Wainwright Zexuan Xu Leonel Lagos Applied Research Center Florida International University Miami USA Electrical and Computer Engineering Florida International University Miami USA Nuclear Science and Engineering Massachusetts Institute of Technology Cambridge USA Climate Dept Lawrence Berkeley National Laboratory Berkeley USA Moss Department Of Construction Management Florida International University Miami USA

ISBN: (数字)9798350391213

ISBN: (纸本)9798350391220

Advances in sensor technology have greatly enhanced the monitoring and assessment of environmental conditions. However, groundwater monitoring presents unique challenges, primarily in accurately detecting anomalies amidst sensor noise, fluctuations, and other inconsistencies in the data. The introduction of low-cost in-situ sensors has dramatically increased data volumes, requiring more advanced analytical techniques. This paper investigates the potential of Artificial Intelligence and Machine Learning (AI/ML), specifically Long Short-Term Memory (LSTM) Autoencoder models and Transformers, to tackle these challenges. LSTM Autoencoders, a specialized form of recurrent neural networks, are well-suited for sequential data analysis and anomaly detection, particularly in time-based sensor readings. The LSTM Autoencoder can compress the data and reconstruct normal patterns by training on historical sensor data representing normal groundwater conditions, thus identifying deviations that signal potential contamination. Meanwhile, transformer models, known for their attention mechanism and ability to capture long-range dependencies, are incorporated to enhance further their ability to distinguish between natural data variations and significant anomalies in complex, dynamic groundwater environments. We apply these LSTM Autoencoder and Transformer approaches to US-DoE Savannah River Site F-Area datasets, demonstrating their robustness and adaptability in identifying subtle and progressive groundwater contamination. This approach improves the accuracy of groundwater monitoring and supports a proactive stance in environmental preservation and public health protection.

关键词： Attention mechanisms Groundwater Autoencoders Transformers Data models Rivers Public healthcare Protection Long short term memory Contamination

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Image Shadow Removal Challenge Report

NTIRE 2023 Image Shadow Removal Challenge Report

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Vasluianu, Florin-Alexandru Seizinger, Tim Timofte, Radu Cui, Shuhao Huang, Junshi Tian, Shuman Fan, Mingyuan Zhang, Jiaqi Zhu, Li Wei, Xiaoming Wei, Xiaolin Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Dong, Xiaoyi Zhang, Xi Sheryl Li, Chenghua Leng, Cong Yeo, Woon-Ha Oh, Wang-Taek Lee, Yeo-Reum Ryu, Han-Cheol Luo, Jinting Jiang, Chengzhi Han, Mingyan Wu, Qi Lin, Wenjie Yu, Lei Li, Xinpeng Jiang, Ting Fan, Haoqiang Liu, Shuaicheng Xu, Shuning Song, Binbin Chen, Xiangyu Zhang, Shile Zhou, Jiantao Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Wang, Bo Ren, Jiahuan Luo, Yan Kondo, Yuki Miyata, Riku Yasue, Fuma Naruki, Taito Ukita, Norimichi Chang, Hua-En Yang, Hao-Hsiang Chen, Yi-Chung Chiang, Yuan-Chun Huang, Zhi-Kai Chen, Wei-Ting Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Xianwei, Li Fu, Huiyuan Liu, Chunlin Ma, Huadong Fu, Binglan He, Huiming Wang, Mengjia She, Wenxuan Liu, Yu Nathan, Sabari Kansal, Priya Zhang, Zhongjian Yang, Huabin Wang, Yan Zhang, Yanru Phutke, Shruti S. Kulkarni, Ashutosh Khan, Md Raqib Murala, Subrahmanyam Vipparthi, Santosh Kumar Ye, Heng Liu, Zixi Yang, Xingyi Liu, Songhua Wu, Yinwei Jing, Yongcheng Yu, Qianhao Zheng, Naishan Huang, Jie Long, Yuhang Yao, Mingde Zhao, Feng Zhao, Bowen Ye, Nan Shen, Ning Cao, Yanpeng Xiong, Tong Xia, Weiran Li, Dingwen Xia, Shuchen Computer Vision Lab Ifi Caidas University of Würzburg Germany Computer Vision Lab Eth Zürich Switzerland Meituan Group China Department of Information Technology Uppsala University Sweden Institute of Automation Chinese Academy of Sciences Beijing China Nanjing China Maicro Nanjing China Department of Artificial Intelligence Convergence Sahmyook University Seoul Korea Republic of Megvii Technology China University of Electronic Science and Technology of China China University of Macau China China Toyota Technological Institute Japan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Beijing University of Post and Teleconmunication Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education China Couger Inc. Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Punjab Rupnagar India Research Institute Singapore National University of Singapore Singapore Research Institute Singapore University of Sydney Australia Brain-Inspired Vision Laboratory Information Science and Technology Institution University of Science and Technology of China China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China South China University of Technology China

ISBN: (纸本)9798350302493

This work reviews the results of the NTIRE 2023 Challenge on Image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs of real shadow free and shadow affected images, captured in a controlled environment. The data was captured in a white-box setup, using professional equipment for lights and data acquisition sensors. The challenge had a number of 144 participants registered, out of which 19 teams were compared in the final ranking. The proposed solutions extend the work on shadow removal, improving over the performance level describing state-of-the-art methods. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Investigation of Positive Bias Temperature Instability in advanced FinFET nodes

Investigation of Positive Bias Temperature Instability in ad...

引用

Annual International Symposium on Reliability Physics

作者： Yongkang Xue Miaojia Yuan Yu Li Da Wang Maokun Wu Pengpeng Ren Lining Zhang Runsheng Wang Zhigang Ji Ru Huang National Key Laboratory of Advanced Micro and Nano Manufacture Technology Shanghai Jiao Tong University Shanghai China Department of Micro/Nano Electronics School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Electronic and Computer Engineering Peking University Shenzhen China School of Integrated Circuits Peking University Beijing China

ISBN: (数字)9798350369762

ISBN: (纸本)9798350369779

PBTI in advanced FinFET nodes has been characterized and modelled by leveraging the efficient defect separation technology in this paper. Two types of traps are identified, including Type-B e1 and Type-B e2 , which can be well described by incorporating the activation state into the two-state NMP theory. Type-B e1 located in the IL layer and may originate from Vo or HB in SiO 2. Type-B e2 located in the HK layer but its physical origin is still unclear. The physical model of each type of traps is established and the predictive capability under DC&AC conditions, long-term reliability under low stress voltage and arbitrary waveform conditions are verified. Finally, by simplifying the physical model into a compact form and embedding it into commercial EDA software, the impact of PBTI on circuit performance is evaluated, and the safe operating voltage range of the circuit is analyzed, which provides guidance for designers to improve the reliability and life of the product.

关键词： Voltage Reliability theory Predictive models Reliability engineering FinFETs Software Software reliability

来源：评论

学校读者我要写书评

暂无评论

Creating embedded radiofrequency structures using polyjet material jetting 26

Creating embedded radiofrequency structures using polyjet ma...

引用

26th Annual International Solid Freeform Fabrication Symposium - An Additive Manufacturing Conference, SFF 2015

作者： Dumene, Richard L. Kennedy, Paul Williams, Christopher B. Sweeney, Dennis Earle, Greg Design Research and Education for Additive Manufacturing Systems Laboratory Department of Mechanical Engineering Virginia Tech United States Director of Instructional Laboratories Bradley Department of Electrical and Computer Engineering Center for Space Science and Engineering Research Bradley Department of Electrical and Computer Engineering

Embedding of integrated systems via Additive Manufacturing (AM) offers the potential to save weight, space, and time in the production of electronics and vehicles. Of specific interest are embedded electrical systems that operate in the radiofrequency (RF) range as they have great potential utility in communication systems and aircraft avionics including navigation. However, systems in this frequency range pose unique manufacturing challenges such as the need to minimize impedance discontinuities in the system. In this work, the authors explore various techniques for embedding RF structures such as antennas and filters via a multi-material jetting AM process. Specifically, the dielectric constants and loss tangents of Vero White and Tango Black polymers were determined to facilitate the design of RF structures with these materials. It is shown that measurements of S-parameters of the resultant embedded RF structures approach or match the performance of non-embedded electronics. © SFF *** rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Vector Field Attention for Deformable Image Registration

arXiv

引用

arXiv 2024年

作者： Liu, Yihao Chen, Junyu Zuo, Lianrui Carass, Aaron Prince, Jerry L. Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States Department of Radiology and Radiological Science Johns Hopkins School of Medicine BaltimoreMD21287 United States Laboratory of Behavioral Neuroscience National Institute on Aging National Institute of Health BaltimoreMD21214 United States

Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over traditional algorithms as well as their better accuracy. Most existing deep learning-based methods require neural networks to encode location information in their feature maps and predict displacement or deformation fields though convolutional or fully connected layers from these high-dimensional feature maps. In this work, we present Vector Field Attention (VFA), a novel framework that enhances the efficiency of the existing network design by enabling direct retrieval of location correspondences. VFA uses neural networks to extract multi-resolution feature maps from the fixed and moving images and then retrieves pixel-level correspondences based on feature similarity. The retrieval is achieved with a novel attention module without the need of learnable parameters. VFA is trained end-to-end in either a supervised or unsupervised manner. We evaluated VFA for intra- and inter-modality registration and for unsupervised and semi-supervised registration using public datasets, and we also evaluated it on the Learn2Reg challenge. Experimental results demonstrate the superior performance of VFA compared to existing methods. The source code of VFA is publicly available at https://***/yihao6/vfa/. Copyright © 2024, The Authors. 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

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：