检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liu, Yunsong Mandal, Debdut Liao, Congyu Setsompop, Kawin Haldar, Justin P. Signal and Image Processing Institute Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States Departments of Radiology and Electrical Engineering Stanford University StanfordCA94305 United States

We introduce a new algorithm to solve a regularized spatial-spectral image estimation problem. Our approach is based on the linearized alternating directions method of multipliers (LADMM), which is a variation of the popular ADMM algorithm. Although LADMM has existed for some time, it has not been very widely used in the computational imaging literature. This is in part because there are many possible ways of mapping LADMM to a specific optimization problem, and it is nontrivial to find a computationally efficient implementation out of the many competing alternatives. We believe that our proposed implementation represents the first application of LADMM to the type of optimization problem considered in this work (involving a linear-mixture forward model, spatial regularization, and nonnegativity constraints). We evaluate our algorithm in a variety of multiparametric MRI partial volume mapping scenarios (diffusion-relaxation, relaxation-relaxation, relaxometry, and fingerprinting), where we consistently observe substantial (∼3×-50×) speed improvements. We expect this to reduce barriers to using spatially-regularized partial volume compartment mapping methods. Further, the considerable improvements we observed also suggest the potential value of considering LADMM for a broader set of computational imaging problems. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

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

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Higher-Order Organization in the Human Brain From Matrix-Based Rényi’s Entropy

Higher-Order Organization in the Human Brain From Matrix-Bas...

引用

Acoustics, Speech, and Signal processing Workshops (ICASSPW), IEEE International Conference on

作者： Qiang Li Shujian Yu Kristoffer H Madsen Vince D Calhoun Armin Iraji Image Processing Laboratory University of Valencia Spain Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS) USA Department of Computer Science Vrije Universiteit Amsterdam The Netherlands Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Danish Research Centre for Magnetic Resonance Copenhagen University Hospital Denmark

Pairwise metrics are often employed to estimate statistical dependencies between brain regions, however they do not capture higher-order information interactions. It is critical to explore higher-order interactions that go beyond paired brain areas in order to better understand information processing in the human brain. To address this problem, we applied multivariate mutual information, specifically, Total Correlation and Dual Total Correlation to reveal higher-order information in the brain. In this paper, we estimate these metrics using matrix-based Rényi ’ s entropy, which offers a direct and easily interpretable approach that is not limited by direct assumptions about probability distribution functions of multivariate time series. We applied these metrics to resting-state fMRI data in order to examine higher-order interactions in the brain. Our results showed that the higher-order information interactions captured increase gradually as the interaction order increases. Furthermore, we observed a gradual increase in the correlation between the Total Correlation and Dual Total Correlation as the interaction order increased. In addition, the significance of Dual Total Correlation values compared to Total Correlation values also indicate that the human brain exhibits synergy dominance during the resting state.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Blockchain-Based Solutions in the Internet of Things 6th

Privacy-Preserving Blockchain-Based Solutions in the Interne...

引用

6th EAI International Conference on science and Technologies for Smart Cities, SmartCity 2020

作者： Zapoglou, Nikolaos Patsakos, Ioannis Drosatos, George Rantos, Konstantinos Department of Computer Science International Hellenic University Kavala Greece Institute for Language and Speech Processing Athena Research Center Xanthi Greece

ISBN: (纸本)9783030760625

Internet of Things (IoT) is a promising, relatively new technology that develops "smart" networks with a variety of uses and applications (e.g., smart cities, smart home and autonomous cars). The diversity of protocols, technologies and devices that IoT consists of, even though they add in value and utility, they create major privacy issues that can be exploited by malicious entities to benefit from or even violate privacy of IoT users. The special features of blockchain technology, such as immutability, transparency, accessibility, autonomy and decentralisation, has led the academics and the industry to search for further uses of it, besides financial applications (e.g., Bitcoin) that was initially applied. This paper is a survey on the existing literature regarding blockchain-based privacy-preserving solutions that have been proposed specifically for the IoT to address personal data protection and preserve user privacy. © 2021, ICST institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Remarks on Gibbs Permutation Matrices for Ternary Bent Functions

Remarks on Gibbs Permutation Matrices for Ternary Bent Funct...

引用

International Symposium on Multiple-Valued Logic

作者： Radomir S. Stanković Milena Stanković Claudio Moraga Jaakko T. Astola Mathematical Institute of SASA Belgrade Serbia Department of Computer Science Faculty of Electronic Engineering Niš Serbia Faculty of Computer Science Technical University of Dortmund Dortmund Germany Department of Signal Processing Tampere University of Technology Tampere Finland

As in the binary case, ternary bent functions are a very small portion of the set of all ternary functions for a given number of variables. For example, for n = 2, there are 486 ternary bent functions out of 19683 ternary functions, which is 2, 47%, and this number reduces exponentially with the increase of n. However, finding, or alternatively, constructing them is a challenging task. A possible approach is based upon the manipulation of known ternary bent functions to construct other ternary bent functions. In this paper, we define Gibbs permutation matrices derived from the Gibbs derivative with respect to the Vilenkin-Chrestenson transform and propose their usage in constructing bent functions. The method can be extended to p-valued bent functions, where p is a prime larger than 3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Repeatability of Dimensional Accuracy and Mechanical Properties in Powder Bed Fusion of 16MnCr5 using a Laser Beam 17

Repeatability of Dimensional Accuracy and Mechanical Propert...

引用

17th CIRP Conference on computer Aided Tolerancing, CAT 2022

作者： Schmitt, Matthias Schlick, Georg Schilp, Joahnnes Fraunhofer-Institute for Casting Composite and Processing Technology IGCV Am Technologiezentrum 10 Augsburg86159 Germany University of Augsburg Chair of Digital Manufacturing Department of Applied Computer Science Universitaetsstraße 2 Augsburg86159 Germany

Additive manufacturing, especially powder bed fusion using a laser beam of metals (PB-LB/M), allows the build-up of complex parts. Therefore, PBF-LB/M is already used in multiple fields, such as medical or aerospace industry. To promote the use of AM within the automotive sector materials such as case-hardening steels have been developed for PBF-LB/M to manufacture drivetrain parts e.g. gears. However, the automotive industry requires strict tolerances and repeatability in the manufacturing processes. At first, the repeatability of specimens built with the case-hardening steel 16MnCr5 within one build plate is investigated. Therefore, the dimensional accuracy in x-, y- and z-direction is measured and ISO basic tolerances are derived. Additionally, the density of specimens within one build plate is determined. Both results are linked to the recoating direction and the occurring gas flow. In a second step, the repeatability between subsequent build jobs is analyzed. The tensile strength of specimens manufactured in 12 build jobs of similar layout is investigated showing high repeatability with properties exceeding conventional material. The occurring tolerances of more than 80 Type 1 gears in 20 build jobs are aggregated to evaluate the process capability of the PBF-LB/M process. © 2022 Elsevier B.V.. All rights reserved.

关键词： Laser beams

来源：评论

学校读者我要写书评

暂无评论

Multi-frame and multi-scale conditional generative adversarial networks for efficient foreground extraction 4th

Multi-frame and multi-scale conditional generative adversari...

引用

4th International Conference on computer Vision and image processing, CVIP 2019

作者： Didwania, Himansu Ghatak, Subhankar Rup, Suvendu Image and Video Processing Lab Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar Bhubaneswar751003 India

ISBN: (纸本)9789811540172

Alongside autonomous submissions, foreground extraction is considered to be the foundation for various video content analysis technologies, like moving object tracking, video surveillance and video summarization. This paper proposes an efficient foreground extraction methodology based on conditional Generative Adversarial Network. The proposed generator, which is made up of two networks working in series- Foreground Extractor and Segmentation Network, maps the video frames to corresponding foreground masks. The discriminator aids the learning of generator by learning to differentiate between seemingly real and fake foreground maps. The method used a multi-scale approach in order to capture robust features across multiple scales of input using the Feature Extractor Network, which are then used by the successive Segmentation Network to produce the final foreground map. In addition, a multi-frame approach is also used to facilitate capturing of appropriate temporal features. The performance of the proposed model is evaluated on CDnet 2014 Dataset and outperforms existing methods. © Springer Nature Singapore Pte Ltd 2020.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

4D foetal cardiac ultrasound image detection based on deep learning with weakly supervised localisation for rapid diagnosis of evolving hypoplastic left heart syndrome

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1485-1499页

作者： Gang Wang Weisheng Li Mingliang Zhou Haobo Zhu Guang Yang Choon Hwai Yap Chongqing Key Laborotory of Image Rocognition Chongqing University of Posts and TelecommunicationsChongqingChina School of Computing and Data Engineering NingboTech UniversityNingboChina Department of Bioengineering Imperial College LondonLondonUK Key Laboratory of Cyberspace Big Data Intelligent Security(Chongqing University of Posts and Telecommunications) Ministry of EducationChongqingChina School of Computer Science Chongqing UniversityChongqingChina University of Oxford OxfordUK Cardiovascular Research Centre Royal Brompton HospitalLondonUK National Heart and Lung Institute Imperial College LondonLondonUK

Hypoplastic left heart syndrome(HLHS)is a rare,complex,and incredibly foetal congenital heart *** decrease neonatal mortality,evolving HLHS(eHLHS)in pregnant women should be critically diagnosed as soon as ***,diagnosis is currently heavily dependent on skilled medical professionals using foetal cardiac ultrasound images,making it difficult to rapidly and easily examine for this ***,the authors propose a cost-effective deep learning framework for rapid diagnosis of eHLHS(RDeH),which we have named ***,the framework implements a coarseto-fine two-stage detection approach,with a structure classification network for 4D human foetal cardiac ultrasound images from various spatial and temporal domains,and a fine detection module with weakly-supervised localisation for high-precision nidus localisation and physician *** experiments extensively compare the authors’network with other state-of-the-art methods on a 4D human foetal cardiac ultrasound image dataset and show two main benefits:(1)it achieved superior average accuracy of 99.37%on three categories of foetal ultrasound images from different cases;(2)it demonstrates visually fine detection performance with weakly supervised *** framework could be used to accelerate the diagnosis of eHLHS,and hence significantly lessen reliance on experienced medical physicians.

关键词： 4D deep learning fetal cardiac ultrasound hypoplastic left heart syndrome weakly-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Automated Pipeline for Tumour-Infiltrating Lymphocyte Scoring in Breast Cancer

An Automated Pipeline for Tumour-Infiltrating Lymphocyte Sco...

引用

IEEE International Symposium on Biomedical Imaging

作者： Adam J Shephard Mostafa Jahanifar Ruoyu Wang Muhammad Dawood Simon Graham Kastytis Sidlauskas Syed Ali Khurram Nasir M Rajpoot Shan E Ahmed Raza Department of Computer Science Tissue Image Analytics Centre University of Warwick UK Barts Cancer Institute Queen Mary University of London UK School of Clinical Dentistry University of Sheffield UK

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Tumour-infiltrating lymphocytes (TILs) are considered as a valuable prognostic markers in both triple-negative and human epidermal growth factor receptor 2 (HER2) positive breast cancer. In this study, we introduce an innovative deep learning pipeline based on the Efficient-UNet architecture to predict the TILs score for breast cancer whole-slide images (WSIs). We first segment tumour and stromal regions in order to compute a tumour bulk mask. We then detect TILs within the tumour-associated stroma, generating a TILs score by closely mirroring the pathologist’s workflow. Our method exhibits state-of-the-art performance in segmenting tumour/stroma areas and TILs detection, as demonstrated by internal cross-validation on the TiGER Challenge training dataset (195 WSIs) and evaluation on the final leaderboards (38 WSIs). Additionally, our TILs score proves competitive in predicting survival outcomes within the same challenge (707 WSIs), underscoring the clinical relevance and potential of our automated pipeline as a breast cancer prognostic tool.

关键词： Training Deep learning image segmentation Pipelines computer architecture Epidermis Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Domain Generalization Algorithms in Computational Pathology

arXiv

引用

arXiv 2024年

作者： Zamanitajeddin, Neda Jahanifar, Mostafa Xu, Kesi Siraj, Fouzia Rajpoot, Nasir Tissue Image Analytics centre Department of Computer Science University of Warwick Coventry United Kingdom Histofy Ltd Coventry United Kingdom ICMR-National Institute of Pathology New Delhi India

Deep learning models have shown immense promise in computational pathology (CPath) tasks, but their performance often suffers when applied to unseen data due to domain shifts. Addressing this requires domain generalization (DG) algorithms. However, a systematic evaluation of DG algorithms in the CPath context is lacking. This study aims to benchmark the effectiveness of 30 DG algorithms on 3 CPath tasks of varying difficulty through 7,560 cross-validation runs. We evaluate these algorithms using a unified and robust platform, incorporating modality-specific techniques and recent advances like pretrained foundation models. Our extensive cross-validation experiments provide insights into the relative performance of various DG strategies. We observe that self-supervised learning and stain augmentation consistently outperform other methods, highlighting the potential of pretrained models and data augmentation. Furthermore, we introduce a new pan-cancer tumor detection dataset (HISTOPANTUM) as a benchmark for future research. This study offers valuable guidance to researchers in selecting appropriate DG approaches for CPath tasks. © 2024, CC BY-NC-SA.

关键词： Self-supervised 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：