检索结果-内蒙古大学图书馆

PCA: Semi-Supervised Segmentation with Patch Confidence Adversarial Training

IEEE Transactions on Network Science and engineering 2025年

作者： Xu, Zhenghua Yang, Runhe Xu, Zihang Zhang, Shuo Yang, Yuchen Liu, Weipeng Xu, Weichao Chen, Junyang Lukasiewicz, Thomas Leung, Victor C. M. Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Tianjin China The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong The Johns Hopkins University Department of Applied Mathematics and Statistic Baltimore United States Hebei University of Technology School of Artificial Intelligence Tianjin China Hebei Provincial Hospital of Traditional Chinese Medicine Digestive Disease Center Shijiazhuang China Shenzhen University College of Computer Science and Software Engineering Shenzhen China University of Oxford Department of Computer Science University of Oxford United Kingdom Department of Computer Science United Kingdom Vienna University of Technology institute of Logic and Computation nstitute of Logic and Computation Vienna Austria

Deep-learning-based semi-supervised learning (SSL) methods have achieved a strong performance in medical image segmentation, which can alleviate doctors' expensive annotation by utilizing a large amount of unlabeled data. Unlike most existing semi-supervised learning methods, adversarial training methods distinguish samples from different sources by learning the data distribution of the segmentation map, leading the segmenter to generate more accurate predictions. We argue that the current performance restrictions for such approaches are the problems of feature extraction and learning preferences. In this paper, we propose a new semi-supervised adversarial method called Patch Confidence Adversarial Training (PCA) for medical image segmentation. The PCA method's discriminator penalizes patch-level structures, guiding the generator to optimize different patch areas, by leveraging pixel context, the generator is driven to focus on high-frequency features, making it harder to deceive the discriminator and easy to converge to an ideal state, which more effectively guides the segmenter to generate high-quality pseudo-labels. Furthermore, at the discriminator's input, we supplement image information constraints, making it simpler to fit the expected data distribution. Extensive experiments on the Automated Cardiac Diagnosis Challenge (ACDC) 2017 dataset and the Brain Tumor Segmentation (BraTS) 2019 challenge dataset show that our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation. © 2025 IEEE. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

SE-FCA: A Model of software Evolution with Formal Concept Analysis

引用

Chinese Journal of Electronics 2015年第1期24卷 13-19页

作者： SUN Xiaobing LI Bixin LI Bin CHEN Ying School of Information Engineering Yangzhou University State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering Southeast University

softwares are naturally evolved to cope with various changing system requirements. software evolution includes a series of activities to analyze, assess, and validate the changes. This paper proposes an integrated software evolution model, namely SE-FCA, to support four core software evolution activities: program comprehension,change impact analysis, regression testing, and fault localization. These four activities are integrated and supported under the formal concept analysis technique, which is efficient to deal with the relation between entities and entity properties to provide a remarkable insight into the structure of the original relation. These activities are evaluated in a unified empirical environment. The empirical study shows the effectiveness of these activities under the SEFCA model.

关键词： Formal concept analysis software evolution software change

来源：评论

学校读者我要写书评

暂无评论

Intelligent transportation systems for smart cities:a progress review

引用

Science China(Information Sciences) 2012年第12期55卷 2908-2914页

作者： COOPER Dave E State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University

To better meet the challenge of providing effective,low-cost,energy efficient transport services,the concept of intelligent transport systems(ITS) has been proposed and lauded as an innovative and promising solution for next generation transport *** this paper,the progress of ITS research around the world is briefly reviewed and current challenges are outlined,thereby offering further insight into ITS development for all researchers in this area.

关键词： intelligent transportation systems traffic information smart city

来源：评论

学校读者我要写书评

暂无评论

Two Generic Frameworks of Multiple Viewpoints Oriented Requirements Method and Their Comparison

引用

Wuhan University Journal of Natural Sciences 2001年第Z1期6卷 313-319页

作者： Song Qiang, He Yan xiang, Huang Qian School of computer Science, State key laboratory of software engineering, Wuhan University, Wuhan 430072, China School of Computer Science State Key Laboratory of Software Engineering Wuhan University Wuhan China

Traditional requirements method has some problems when it is used for large distributed systems. Multiple viewpoints oriented requirements method (MVORM) is a new method for resolving these problems. This paper develops two generic formal frameworks of MVORM, framework based on refinement relation (FBRR) and framework based on implementation relation (FBIR). They are generic, because no assumptions are made about the development process or the formal description languages to be used. Three kinds of specification relations and three kinds of specification transformations are discussed over FBIR and FBRR. This paper also compares the equivalence between FBIR and FBRR. We point out that an equivalent FBIR can be found for any FBRR, but reverse transformation is not always possible. We think FBIR is better than FBRR on most cases.

关键词： multiple viewpoints oriented requirements method framework based on refinement relation framework based on implementation relation refinement relation implementation relation

来源：评论

学校读者我要写书评

暂无评论

Formalization of Rules for the Cooperation between Goal and Process

引用

Journal of Donghua University(English Edition) 2012年第1期29卷 32-36页

作者：李昭李征李宏涛梁鹏何克清刘书宇 State Key Laboratory of Software Engineering Wuhan University Computer School Wuhan University

To meet the end-user's dynamically changed requirements for software and achieve the on-demand changes of operational process in time, based on the Goal model and the Process model, the user's personalized operations of the related work were simplified and integrated, and rules for the cooperation between Goal and Process which fit for software engineers were proposed and formalized. The user's personalized operations of the related work were analyzed to conclude the pattern of Goal modification. By the direct drive of Goal modification, the corresponding changes of Process were induced and specified. Then rules for the cooperation between Goal and Process were concluded and the formalization was achieved in Semantic Web Rule Language (SWRL). In this paper, reasoning support was provided for the model modification based on ontology and the dynamic evolution of Process model.

关键词： personalized reguirements on-demand services Goal and Process rules for the cooperation formalization

来源：评论

学校读者我要写书评

暂无评论

Research on Evolution of Goal-Driven Service Composition Patterns

引用

Journal of Donghua University(English Edition) 2012年第1期29卷 14-18页

作者：李征李昭何克清王健冯在文 State Key Laboratory of Software Engineering Wuhan University Computer School Wuhan University

With the development of Web service technology, using composite services to satisfy users' requirements has become an inevitable tendency. Goal changes caused by changing requirements of users may directly drive the corresponding evolution of service composition. However, most researches focus on how to compose services, and little efforts have been placed on how to evolve the composite services with changing requirements. In this paper, the service composition patterns are defined based on workflow patterns, and the changes of service composition patterns are analyzed according to changing goals. Finally, a case study is given to demonstrate the feasibility of the proposed approach.

关键词： workflow pattern service composition pattern goal evolution

来源：评论

学校读者我要写书评

暂无评论

A parallel and robust object tracking approach synthesizing adaptive Bayesian learning and improved incremental subspace learning

引用

Frontiers of computer Science 2019年第5期13卷 1116-1135页

作者： Kang LI Fazhi HE Haiping YU Xiao CHEN State Key Laboratory of Software Engineering School of Computer Science Wuhan University Wuhan 430072 China School of Computer Science and Information Engineering Hubei University Wuhan 430062 China

This paper presents a novel tracking algorithm which integrates two complementary trackers. Firstly, an improved Bayesian tracker(B-tracker) with adaptive learning rate is presented. The classification score of B-tracker reflects tracking reliability, and a low score usually results from large appearance change. Therefore, if the score is low, we decrease the learning rate to update the classifier fast so that B-tracker can adapt to the variation and vice versa. In this way, B-tracker is more suitable than its traditional version to solve appearance change problem. Secondly, we present an improved incremental subspace learning method tracker(Stracker). We propose to calculate projected coordinates using maximum posterior probability, which results in a more accurate reconstruction error than traditional subspace learning tracker. Instead of updating at every time, we present a stopstrategy to deal with occlusion problem. Finally, we present an integrated framework(BAST), in which the pair of trackers run in parallel and return two candidate target states separately. For each candidate state, we define a tracking reliability metrics to measure whether the candidate state is reliable or not, and the reliable candidate state will be chosen as the target state at the end of each frame. Experimental results on challenging sequences show that the proposed approach is very robust and effective in comparison to the state-of-the-art trackers.

关键词： object tracking Bayesian learning subspace learning particle filter principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Reusing Service Process Fragments with a Consensus Between Service Providers and Users

引用

Chinese Journal of Electronics 2016年第4期25卷 648-657页

作者： YANG Rong LI Bing WANG Jian LI Zengyang HU Yan College of Computer Science and Technology Hubei University of Science and Technology International School of Software Wuhan University State Key Laboratory of Software Engineering & School of Computer Wuhan University Science and Technology on Integrated Information System Laboratory Institute of SoftwareUniversity of Chinese Academy of Sciences

Recent years have witnessed a rapid growth in using Web services for data publishing and sharing among *** improve the efficiency of software development and economize on human and material resources,service reuse is viewed as a powerful means which will not only reuse atomic services,but also reuse arbitrary granularities of Service process fragments(SPFs).However,effectively reusing arbitrary granularities of SPFs has not been solved yet,let alone taking diverse Qo S preferences of service providers and users into *** this paper,we propose a novel method of SPF reuse,named SCKY,based on the Cocke-Kasami-Younger(CKY) *** first present an extended CKY to do *** we address how to do SPF-query by a probability CKY,i.e.,return a SPF with maximum emergence ***,we explore the SPF-query with a consensus of Qo S preferences between service providers and *** a set of experiments,the effectiveness and robustness of our approach are evaluated.

关键词： Cocke-Kasami-Younger algorithm Service reuse Service process fragment Qo S preferences

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty Enhanced Trust Evolution Strategy for e-Science

引用

Journal of computer Science & Technology 2010年第6期25卷 1225-1236页

作者：杜薇崔国华刘伟 School of Computer Science and Technology Huazhong University of Science and Technology College of Computer Science and Technology Wuhan University of Technology State Key Lab of Software Engineering Wuhan University State Key Laboratory for Novel Software Technology Nanjing University

Resources shared in e-Science have critical requirements on *** subjective trust management is essential to guarantee users＇ collaborations and communications on such a promising *** an important nature of subjective trust,uncertainty should be preserved and exhibited in trust definition,representation and *** the drawbacks of existing mechanisms based on random mathematics and fuzzy theory,this paper designs an uncertainty enhanced trust evolution strategy based on cloud model *** define subjective trust as trust *** we propose new algorithms to propagate,aggregate and update ***,based on the concept of similar cloud,a method to assess trust level is put *** simulation results show the effiectiveness,rationality and efficiency of our proposed strategy.

关键词： cloud model theory similar cloud operator subjective trust trust cloud

来源：评论

学校读者我要写书评

暂无评论

Neural Rendering and Flow-assisted Unsupervised Multi-view Stereo for Real-time Monocular Tracking and Scene Perception

引用

IEEE Transactions on Automation Science and engineering 2025年

作者： Tong, Kevin W. Cai, Yandong Jie, Yu-Wen Duan, Ya Hou, Yuhong Wu, Edmond Q. Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Dalian116024 China Shanxi University School of Automation and Software Engineering Shanxi 237016 China Flight Test Technology and Engineering Center of the Chinese Flight Test Establishment Xian710089 China China Civil Aviation Shanghai Aircraft Airworthiness Certification Center Shanghai200335 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

The existing camera tracking and perception methods mainly rely on sparse SLAM, which limits the dense perception ability of the scene and affects the reliability of auxiliary decision-making. Different from this, this work proposes a real-time tracking and unsupervised dense sensing framework. Firstly, the dense depth value of the scene is predicted by unsupervised multi-view stereo to remove the dependence on labeled data. Then, the quality of synthetic pseudo-reference image is quantified according to the predicted depth map and used as a weighted guidance to train the unsupervised model, thus reducing the ambiguity of feature matching in areas such as specular reflection. Moreover, the sparse optical flow of the keyframes is solved by real-time and robust ORB feature matching operator, which assists the high-precision training of unsupervised depth inference model. To increase the prediction accuracy of occluded area, a novel rendering consistency loss via neural radiance fields is designed to constrain the geometric characteristics of object surface. Finally, dense direct image alignment is performed from a global model to improve the tracking robustness, which is incrementally constructed from dense depth prediction. Extensive experiments on synthetic datasets and real datasets validate the effectiveness and practicability of the proposed work, which is an effective supplement to the existing SLAM work. © 2025 IEEE.

关键词： Stereo image processing

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：