检索结果-内蒙古大学图书馆

DiffuSeg: Domain-driven Diffusion for Medical Image Segmentation

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3619-3631页

作者： Zhang, Le Wu, Fuping Bronik, Kevin Papiez, Bartlomiej W. University of Birmingham School of Engineering College of Engineering and Physical Sciences Birmingham United Kingdom University of Oxford Big Data Institute Li Ka Shing Centre for Health Information and Discovery Nuffield Department of Population Health Oxford United Kingdom University of Oxford Department of Engineering Science Oxford United Kingdom

In recent years, the deployment of supervised machine learning techniques for segmentation tasks has significantly increased. Nonetheless, the annotation process for extensive datasets remains costly, labor-intensive, and error-prone. While acquiring sufficiently large datasets to train deep learning models is feasible, these datasets often experience a distribution shift relative to the actual test data. This problem is particularly critical in the domain of medical imaging, where it adversely affects the efficacy of automatic segmentation models. In this work, we introduce DiffuSeg, a novel conditional diffusion model developed for medical image data, that exploits any labels to synthesize new images in the target domain. This allows a number of new research directions, including the segmentation task that motivates this work. Our method only requires label maps from any existing datasets and unlabelled images from the target domain for image diffusion. To learn the target domain knowledge, a feature factorization variational autoencoder is proposed to provide conditional information for the diffusion model. Consequently, the segmentation network can be trained with the given labels and the synthetic images, thus avoiding human annotations. Initially, we apply our method to the MNIST dataset and subsequently adapt it for use with medical image segmentation datasets, such as retinal fundus images for vessel segmentation and MRI images for heart segmentation. Our approach exhibits significant improvements over relevant baselines in both image generation and segmentation accuracy, especially in scenarios where annotations for the target dataset are unavailable during training. An open-source implementation of our approach can be released after reviewing. © 2013 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Liquid metal assistant self-propagating high-temperature synthesis of S-containing high-entropy MAX-phase materials

引用

材料科学技术（英文版） 2025年第6期209卷 1-8页

作者： Donglong Bai Qiang Wang Bin Deng Yang Li Ao Huang Zitong Cheng Yun Zhao Jing Li Wei Yao Jianguang Xu School of Materials and Energy Shanghai Key Laboratory of Engineering Materials Application and EvaluationShanghai Polytechnic UniversityShanghai 201209China Shanghai Thermophysical Properties Big Data Professional Technical Service Platform Shanghai Engineering Research Center of Advanced Thermal Functional MaterialsShanghai 201209China School of Materials Science and Engineering Yancheng Institute of TechnologyYancheng 224000China School of Materials and Energy Shanghai Key Laboratory of Engineering Materials Application and EvaluationShanghai Polytechnic UniversityShanghai 201209China

Due to their high-entropy effects,the high-entropy(HE)MAX-phase materials improve the comprehen-sive performance of MAX phases,opening up more possibilities for practical engineering ***,it is still challenging to obtain S-containing high-entropy MAX phases because of the high volatilization behavior of sulfur,suffering from issues such as high reaction temperature and long re-action time of traditional synthesis *** paper proposes a novel process named as liquid metal assistant self-propagating high-temperature synthesis(LMA-SHS)for efficient synthesis of high-purity S-containing high-entropy MAX-phase ***-melting-point metal(Sn or In)has been introduced into the raw mixture and melted into a liquid phase during the early stage of the SHS *** serv-ing as a"binder"between transition metal atoms of the M-site due to the negative mixing enthalpy,this liquid phase can accelerate mass and heat transfer during the SHS process,ensuring a uniform solid solution of each element and realizing the synthesis of high-purity(TiNbVZr)2SC in an extremely short *** synthesis method for high-entropy MAX-phase materials developed in this study,i.e.,LMA-SHS,showing very short reaction time,low energy consumption,high yield,and low cost,has the promise to be a general energy-and resource-efficient route towards high-purity HE materials.

关键词： High-entropy S-containing MAX phases Liquid metal LMA-SHS

来源：评论

学校读者我要写书评

暂无评论

Prototype-oriented Clean Subset Extraction for Noisy Long-tailed Classification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Li, Zhuo Zhao, He Gao, Anningzhe Guo, Dandan Chang, Tsung-Hui Wan, Xiang The Chinese University of HongKong School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen China CSIRO's Data61 Australia Shenzhen Research Institute of Big Data China Jilin University School of Artificial Intelligence China

Real-world datasets usually suffer from class imbalance and label noise. To solve the joint challenge of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy from clean samples. While effective, they may be limited in handling the joint issue in a unified way. In this work, we bridge this gap by effectively extracting a clean training subset from the noisy and long-tailed dataset, where we develop a novel re-labeling method using class prototypes from the perspective of distribution matching that can be solved with optimal transport. By using the learned transport plan to re-label training samples and setting a class-specific probability measure, our method can simultaneously reduce the side-effects of label noise and data imbalance during label refinement. Then we introduce a simple yet effective filter by combining the observed and refined labels to obtain a clean subset for robust model training. Comprehensive experiments show that our method can effectively extract clean subsets and bring significant performance gains in noisy long-tailed classification1 © 1991-2012 IEEE.

关键词： long-tailed classification Noisy label optimal transport pseudo-labeling

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of Computer science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

FlexIM: Efficient and Verifiable Index Management in Blockchain

引用

IEEE Transactions on Knowledge and data engineering 2025年第6期37卷 3399-3412页

作者： Li, Binhong Lin, Licheng Zhang, Shijie Xu, Jianliang Xiao, Jiang Li, Bo Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Laboratory The Cluster and Grid Computing Laboratory School of Computer Science and Technology Wuhan430074 China Hong Kong Baptist University School of Computer Science Hong Kong Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong999077 Hong Kong

Blockchain-based query with its traceability and data provenance has become increasingly popular and widely adopted in numerous applications. Yet existing index-based query approaches are only efficient under static blockchain query workloads where the query attribute or type must be fixed. It turns out to be particularly challenging to construct an efficient index for dynamic workloads due to prohibitively long construction time and excessive storage consumption. In this paper, we present FlexIM, the first efficient and verifiable index management system for blockchain dynamic queries. The key innovation in FlexIM is to uncover the inherent characteristics of blockchain, i.e., data distribution and block access frequency, and then to optimally choose the index by utilizing reinforcement learning technique under varying workloads. In addition, we enhance and facilitate verifiability with low storage overhead by leveraging Root Merkle Tree (RMT) and Bloom Filter Merkle Tree (BMT). Our comprehensive evaluations demonstrate that FlexIM outperforms the state-of-the-art blockchain query mechanism, vChain+, by achieving a 26.5% speedup while consuming 94.2% less storage, on average, over real-world Bitcoin datasets. © 1989-2012 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Make an Image Move: Few-Shot Based Video Generation Guided by CLIP 27th

Make an Image Move: Few-Shot Based Video Generation Guided b...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Huang, Yonglong Yu, Cheng Li, Nannan Deng, Fuqin Ge, Ruiquan Wang, Changmiao School of Computer Science and Engineering Macau University of Science and Technology Macau China Chongqing University of Technology Chongqing China Wuyi University Jiangmen China Hangzhou Dianzi University Hangzhou China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (纸本)9783031781711

The recent surge in interest surrounding text-to-video diffusion models highlights their capability to generate videos with both consistency and diversity. Current methods focus on leveraging large-scale datasets to align with training videos, while certain approaches explore the potential of zero-shot generation. Few-shot generative models adapt text-to-image model with temporal layers. They can capture the temporal motion and appearance with acceptable computational resources. However, the prevalent few-shot based approaches, which employ a singular prompt for training videos, typically result in inadequate control over complex backgrounds and multiple objects. To overcome this limitation, we introduce a novel component: the dual cross-attention layer. This component leverages CLIP for image feature extraction. The image feature and text feature will be processed independently in dual cross-attention layer, aiming to achieve image reference and enrich the training videos with additional information. This dual cross-attention mechanism empowers the diffusion model to learn both image and text information effectively, facilitating the generation of higher quality videos. Furthermore, we propose an innovative sampling method to enhance temporal consistency and stability of generative videos. Compared to other text-to-video generative models, our framework demonstrates superior efficiency in generating high quality videos with diverse styles. The code is available at https://***/FatLong666/MAIM. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

ALPS: An Auto-Labeling and Pre-Training Scheme for Remote Sensing Segmentation With Segment Anything Model

引用

IEEE Transactions on Image Processing 2025年 34卷 2408-2420页

作者： Zhang, Song Wang, Qingzhong Liu, Junyi Xiong, Haoyi Institute of Electronics Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100190 China Big Data Laboratory Baidu Research Baidu Inc. Beijing100089 China Aerospace Information Research Institute NIST Institute of Electronics Chinese Academy of Sciences Beijing100190 China

In the fast-growing field of Remote Sensing (RS) image analysis, the gap between massive unlabeled datasets and the ability to fully utilize these datasets for advanced RS analytics presents a significant challenge. To fill the gap, our work introduces an innovative auto-labeling framework named ALPS (Automatic Labeling for Pre-training in Segmentation), which leverages the Segment Anything Model (SAM) to predict precise pseudo-labels for RS images without necessitating prior annotations or additional prompts. The proposed pipeline significantly reduces the labor and resource demands traditionally associated with annotating RS datasets. By constructing two comprehensive pseudo-labeled RS datasets via ALPS for pre-training purposes, our approach enhances the performance of downstream tasks across various benchmarks, including iSAID and ISPRS Potsdam. Experiments demonstrate the effectiveness of our framework, showing its ability to generalize well across multiple tasks even under the scarcity of extensively annotated datasets, offering a scalable solution to automatic segmentation and annotation challenges in the field. In addition, the proposed pipeline is flexible and can be applied to medical image segmentation, remarkably increasing the performance. Note that ALPS utilizes pre-trained SAM to semi-automatically annotate RS images without additional manual annotations. Although every component in the pipeline has been well explored, integrating clustering algorithms with SAM and novel pseudo-label alignment significantly enhances RS segmentation, as an off-the-shelf tool for pre-training data preparation. © 1992-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Security analysis and secured access design for networks of image remote sensing

引用

Digital Communications and Networks 2025年第1期11卷 136-144页

作者： Juan Zhao Haibo Dai Xiaolong Xu Hao Yan Zheng Zhang Chunguo Li School of Network Security Jinling Institute of TechnologyNanjing 211169China School of IoT Nanjing University of Posts and Telecommunications(NJUPT)Nanjing 210003China Jiangsu Key Lab.of Big Data Security and Intelligent Processing NJUPTNanJing 210003China School of Information Science and Engineering Southeast UniversityNanjing 210096China

The secured access is studied in this paper for the network of the image remote *** sensor in this network encounters the information security when uploading information of the images wirelessly from the sensor to the central collection *** order to enhance the sensing quality for the remote uploading,the passive reflection surface technique is *** one eavesdropper that exists nearby this sensor is keeping on accessing the same networks,he may receive the same image from this *** goal in this paper is to improve the SNR of legitimate collection unit while cut down the SNR of the eavesdropper as much as possible by adaptively adjust the uploading power from this sensor to enhance the security of the remote sensing *** order to achieve this goal,the secured energy efficiency performance is theoretically analyzed with respect to the number of the passive reflection elements by calculating the instantaneous performance over the channel fading *** on this theoretical result,the secured access is formulated as a mathematical optimization problem by adjusting the sensor uploading power as the unknown variables with the objective of the energy efficiency maximization while satisfying any required maximum data rate of the eavesdropper ***,the analytical expression is theoretically derived for the optimum uploading *** simulations verify the design approach.

关键词： Image remote sensing Secured access Energy efficiency Sensor transmit power Secured access design

来源：评论

学校读者我要写书评

暂无评论

Service competition in two-tier healthcare markets with heterogeneous patients balking

引用

Journal of Management science and engineering 2025年第1期10卷 18-36页

作者： Yuanbing Miao Xiaoqing Cai Yanfei Lan Ruiqing Zhao Yinlian Zeng College of Management and Economics Tianjin UniversityTianjin300072China School of Data Science The Chinese University of Hong KongShenzhen518172China Shenzhen Research Institute of Big Data Shenzhen518172China College of Urban Transportation and Logistics Shenzhen Technology UniversityShenzhen518118China

Recently,public and private providers within two-tier healthcare markets have engaged in a fierce competition for patients,which is significantly influenced by patients'multifaceted sensitivities to delays and payments,particularly when patients'potential balking is ***,existing literature studying the two-tier healthcare market often presupposes patients as homogeneous or one-dimensionally heterogeneous,and neglects their balking *** stark contrast,this paper delves into the combined effects of patients’delay-and payment-sensitive heterogeneities,alongside their joining or balking decisions,on the service competition dynamics within the two-tier healthcare *** a game-theoretic framework,we initially derive subgame equilibria,both inclusive and exclusive of patient balking,uncovering that patient balking can lead to a subgame perfect Nash equilibrium in the presence of two-dimensional patient ***,our findings further suggest that the non-profit public provider may,counterintuitively,curtail its service capacity despite budgetary adequacy,contradicting the conventional assumption that such providers would fully allocate funds towards patient ***,from a patient welfare standpoint,we find heightened payment heterogeneity discrimination proves detrimental to patients,whereas increased differentiation in delay heterogeneity benefits *** revelation underscores a pressing social issue inherent in the two-tier healthcare market model:It has the potential to exacerbate healthcare disparities rooted in economic inequalities within the population.

关键词： OR in health services Queuing theory Game theory Joining-or-balking behavior

来源：评论

学校读者我要写书评

暂无评论

Wind turbine detection based on high spatial resolution four-band reflectance images 6

Wind turbine detection based on high spatial resolution four...

引用

6th International Conference on Geoscience and Remote Sensing Mapping, GRSM 2024

作者： Deng, Fengying Qiao, Baojun Li, Kaitao Zhao, Limin Chen, Xingfeng Li, Jiaguo Liu, Jun Sun, Yuan Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China Aerospace Information Research Institute Chinese Academy of Science Beijing China School of Space Information Space Engineering University Beijing China

ISBN: (纸本)9781510688018

Wind turbine detection is essential for the power industry and regulatory agencies to efficiently and accurately determine their number and spatial distribution. Under complex underlying surface conditions, the detection accuracy of conventional methods is low, especially when dealing with multi-scale wind turbine targets. In addition, the underutilization of the near-infrared (NIR) band limits the capability of optical remote sensing sensors in wind turbine detection. To address the above problems, this paper proposes a wind turbine detection algorithm YOLOv8m-BD based on high spatial resolution four-band reflectance images using YOLOv8m as the baseline model. Firstly, the four-band image is input through channel adaptation modification. Next, the CSPDarknet53 to 2-stage FPN (C2f) module is enhanced by introducing deformable convolution (DCN) to expand the receptive field. Finally, the effectiveness of our design was validated through extensive experiments on a self-built wind turbine dataset. Compared to the YOLOv8m baseline model that only inputs RGB three bands, the improved YOLOv8m-BD achieves an accuracy of 96.4% and a false alarm rate of 2.0%, an increase of 3.4% in accuracy and a decrease of 2.5% in false alarm rate. © 2025 SPIE.

关键词： Proximity sensors

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：