检索结果-内蒙古大学图书馆

Learning Intrinsic Invariance within Intra-Class for Domain Generalization

IEEE Transactions on Multimedia 2025年

作者： Zhou, Chaoyang Wang, Zengmao Du, Bo Wuhan University School of Computer Science Wuhan430072 China Wuhan University School of Computer Science Artificial Intelligence Institute of Wuhan University National Engineering Research Center for Multimedia Software China Hubei LuoJia Laboratory China

Deep learning methods often struggle with the domain shift problem, leading to poor generalization on out-of-domain (OOD) data. To address the problem, domain generalization (DG) has been proposed to leverage the source domains to train a model that can generalize to OOD data. Existing domain generalization methods primarily focus on learning domain invariance, but they fail to ensure proximity among samples within the same category when domains are aligned for domain-invariant learning. Consequently, their generalization performance remains suboptimal. In this paper, we propose a novel approach to address this issue by iteratively approximating the category domain-invariant distribution from all domains. Our method involves an iterative loop where we initially estimate the domain-invariant distribution for each category by averaging the statistical characteristics across all domains. Then the adversarial perturbation alignment is adopted to keep each sample close to its corresponding category domain-invariant distribution. With the iterative loop, the deep network is optimized for robust domain invariance learning. Extensive experiments demonstrate that our proposed method consistently outperforms state-of-the-art approaches across various scenarios. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

KGCODE-Tab Results for SemTab 2022

KGCODE-Tab Results for SemTab 2022

引用

2022 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, SemTab 2022

作者： Li, Xinhe Wang, Shuxin Zhou, Wei Zhang, Gongrui Jiang, Chenghuan Hong, Tianyu Wang, Peng School of Computer Science and Engineering Southeast University China College of Software Engineering Southeast University China Chien-Shiung Wu College Southeast University China

This paper presents the results of KGCODE-Tab in the tabular data to knowledge graph matching contest SemTab 2022. As an efficient tabular data linking system, KGCODE-Tab is intended to participate in three tasks of the content: Column Type Annotation (CTA), Cell Entity Annotation (CEA), and Columns Property Annotation (CPA). The specific techniques used by KGCODE-Tab will be introduced briefly. The strengths and weaknesses of KGCODE-Tab will also be discussed. © 2022 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Effective Image Representation using Double Colour Histogram for Content-Based Image Retrieval

引用

Informatica (Slovenia) 2021年第7期45卷 97-105页

作者： Martey, Ezekiel Mensah Lei, Hang Li, Xiaoyu Appiah, Obed School of Information & Software Engineering University of Electronic Science and Technology of China China Department of Computer Science and Informatics University of Energy and Natural Resource Ghana

Image representation is critical to the successful realisation of Content-Based Image Retrieval (CBIR) systems. The choice of features to represent the image affects retrieval performance. Nowadays, image databases are heterogeneous and different feature types can be used for appropriate descriptions. This paper proposes an image representation for CBIR that combines Stacked Colour Histogram (SCH) and Conventional Colour Histogram (CCH) to improve image retrieval precision. This presented technique is designed to capture the colour and texture information of the image. The colour properties of an image are represented by CCH and that of texture by SCH. The weighted similarity measure is used to estimate the proportion of similarity values in the retrieval task. The novel descriptor has been widely tested on four standard image datasets, namely Batik, Coil100, Corel10K and Outext. Batik, Coil100 and Outext are used to assess texture discrimination. Corel10K is used to assess the discrimination of heterogeneous images. Experimental results and comparisons with SCH, CMTH, MTH, TCM, CTM and NRFUCTM demonstrate that the proposed descriptor has superior retrieval performance. © 2021 Slovene Society Informatika. All rights reserved.

关键词： Image representation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Built-In Self-Diagnosis and Self-Repair Techniques for Daisy-Chain Design in MEDA Digital Microfluidic Biochips

Enhanced Built-In Self-Diagnosis and Self-Repair Techniques ...

引用

作者： Zhang, Ling Li, Zipeng Huang, Xing Chakrabarty, Krishnendu School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics Nanchang330033 China Department of Electrical and Computer Engineering Duke University DurhamNC27705 United States Silicon Engineering Group Apple Inc. CupertinoCA27705 United States School of Computer Science Northwestern Polytechnical University Xi'an710072 China

Digital microfluidic biochips have emerged as a promising alternative for various laboratory procedures in biochemistry, such as drug discovery and DNA sequencing. A recent generation of digital biochips uses a micro-electrode-dot-array (MEDA) architecture, which provides finer controllability of droplets and seamlessly integrates microelectronics and microfluidics. To simplify the wiring design of such biochips, all microelectrodes and their control registers are daisy-chained together. Therefore, the ability to both identify faults in the chain and tolerate them is required in MEDA biochips. In this study, a new daisy-chain design approach is proposed, integrating a built-in self-repair scheme that can automatically detect faults and correct them. Moreover, an efficient test generation method that requires only a small number of test vectors is proposed to achieve 100% fault coverage without degrading the electrodes. The proposed self-repair scheme can be used in both offline and online modes. Experimental results show that detection and repair can be carried out for various types of faults that can occur in daisy chains. © 2023 IEEE.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Weak Network Oriented Mobile Distributed Storage: A Hybrid Fault-Tolerance Scheme Based on Potential Replicas 24

Weak Network Oriented Mobile Distributed Storage: A Hybrid F...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Wei, Xinlei Tan, Yujuan Liu, Duo Wu, Daitao Wu, Yu Chen, Xianzhang Li, Jian College of Computer Science Chongqing University Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China School of Electrical Engineering Chongqing University Chongqing China

ISBN: (纸本)9798350319934

Node failure is one of the most typical issues in distributed storage systems. The classic fault-tolerance methods can meet the fault tolerance needs of systems deployed in edge storage, 5G IoT, and other high-performance data centers. However, mobile distributed systems contend with inconsistent network signals and relatively low bandwidth in weak network environments. The traditional fault-tolerance schemes have difficulty ensuring distributed storage and data repair simultaneously, posing a considerable challenge to data storage reliability. To address this problem, we proposed a hybrid fault-tolerance scheme based on potential replicas, called HFPR, which trades off storage overhead and performance for weak network mobile distributed storage systems. HFPR first stores data with the erasure code redundancy and then gradually increases data redundancy by reserving potential replicas, enabling the system to disperse network transmission pressure and reduce network transmission. To maximize replica utilization and control the storage overhead of potential replicas, we design a node state prediction mechanism and a file lifecycle management mechanism. Evaluation results show that, compared with the traditional hybrid fault-tolerant scheme with the same storage overhead, HFPR achieves better replica-level repair efficiency in data repair and a reduced probability of degraded reads by approximately 50%. During data distribution, HFPR can minimize data write amplification by up to 1.1× and additional network transfers by up to 77.5%. © 2022 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

3DS: An Efficient DPDK-based Data Distribution Service for Distributed Real-time Applications 24

3DS: An Efficient DPDK-based Data Distribution Service for D...

引用

作者： Xu, Tianyu Chen, Xianzhang Wu, Changze Wang, Jiapin Zheng, Rongwei Liu, Duo Tan, Yujuan Ren, Ao Li, Jian College of Computer Science Chongqing University Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China School of Electrical Engineering Chongqing University Chongqing China

ISBN: (纸本)9798350319934

Data Distribution Service (DDS) is a widely-used middleware for data transmission in distributed real-time applications, such as autonomous vehicles and robotics. However, the communication of existing DDS middlewares generally relies on the network stacks of the operating system, which brings long latency to the real-time applications. In this paper, we propose a DPDK-based DDS, dubbed 3DS, to improve the performance of communication of DDS middlewares. First, 3DS reduces the latency of communication between distributed real-time applications by avoiding the latency of kernel. Second, 3DS reduces the overhead of dynamic memory allocation and deallocation by a reserved memory pool. Finally, 3DS adopts a thread-exclusive CPU model to reduce the resource contention between threads. We implement and evaluate 3DS on real systems running Linux. The experimental results show that 3DS reduces 44% of the communication latency over FastDDS, which is the state-of-the-art DDS middleware used by ROS2. Moreover, the throughput of data transfer in 3DS can be 1.51 times that of FastDDS. © 2022 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

A Survey of Applications of Vision Transformer and its Variants

A Survey of Applications of Vision Transformer and its Varia...

引用

Intelligent Data and Security (IDS), IEEE International Conference on

作者： Chuang Wu Tingqin He Hunan Key Laboratory for Service computing and Novel Software Technology School of Computer Science and Engineering Hunan University of Science and Technology

ISBN: (数字)9798350389487

ISBN: (纸本)9798350389494

The Transformer architecture, renowned for its efficacy in natural language processing, encounters unique hur-dles when applied to computer vision. In response, the Vision Transformer (Vi $T$ ) emerges as a successful adaptation for image classification tasks. While ViT exhibits tremendous potential in revolutionizing computer vision, addressing its inherent chal-lenges and limitations stands as a critical endeavor. This compre-hensive survey meticulously scrutinizes the drawbacks associated with ViT, proposing bespoke adaptations tailored to specific applications while showcasing their remarkable performance across diverse visual tasks. Moreover, it delves into the evolution of ViT adaptations across various visual domains, elucidating four promising directions for future research and development in this dynamic field.

关键词： Surveys computer vision Visualization Computational modeling Transformers Real-time systems Data models

来源：评论

学校读者我要写书评

暂无评论

Ensemble Graph and Device Clustering Method based on Attention Mechanism for Decomposing Monolithic to Microservices

Ensemble Graph and Device Clustering Method based on Attenti...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Qingyong Deng Qiuming Li Qinghua Zuo Shujuan Tian Saiqin Long School of Computer Science and Engineering and the School of Software Guangxi Normal University Guilin China School of Computer Science Xiangtan University Xiangtan China College of Information Science and Technology Jinan University Guangzhou China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Existing methods for decomposing monolithic applications into microservices in cloud environments primarily rely on the call relationships within itself. However, these methods are difficult to apply directly in resource-constrained and distributed edge network scenarios without considering the heterogeneity of the device. Therefore, this paper proposes a clustering method that ensembles graph structures and device features based on attention mechanism, which utilizes attention encoders to learn node embeddings and employs a spectral clustering algorithm to obtain decomposition results, optimizing the affinity and matching degree between microservices and devices. Experimental results demonstrate that the proposed method exhibits excellent performance in terms of functional independence, modularity, and adaptability of microservices.

关键词： Performance evaluation Industries Distributed processing Attention mechanisms Clustering methods Scalability Microservice architectures Clustering algorithms Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Mix-Modality Person Re-Identification: A New and Practical Paradigm

arXiv

引用

arXiv 2024年

作者： Liu, Wei Xu, Xin Chang, Hua Yuan, Xin Wang, Zheng School of Computer Science and Technology Wuhan University of Science and Technology China National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University China

Current visible-infrared cross-modality person re-identification research has only focused on exploring the bi-modality mutual retrieval paradigm, and we propose a new and more practical mix-modality retrieval paradigm. Existing Visible-Infrared person re-identification (VI-ReID) methods have achieved some results in the bi-modality mutual retrieval paradigm by learning the correspondence between visible and infrared modalities. However, significant performance degradation occurs due to the modality confusion problem when these methods are applied to the new mix-modality paradigm. Therefore, this paper proposes a Mix-Modality person re-identification (MM-ReID) task, explores the influence of modality mixing ratio on performance, and constructs mix-modality test sets for existing datasets according to the new mix-modality testing paradigm. To solve the modality confusion problem in MM-ReID, we propose a Cross-Identity Discrimination Harmonization Loss (CIDHL) adjusting the distribution of samples in the hyperspherical feature space, pulling the centers of samples with the same identity closer, and pushing away the centers of samples with different identities while aggregating samples with the same modality and the same identity. Furthermore, we propose a Modality Bridge Similarity Optimization Strategy (MBSOS) to optimize the cross-modality similarity between the query and queried samples with the help of the similar bridge sample in the gallery. Extensive experiments demonstrate that compared to the original performance of existing cross-modality methods on MM-ReID, the addition of our CIDHL and MBSOS demonstrates a general improvement. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Approximated Coded Computing: Towards Fast, Private and Secure Distributed Machine Learning

引用

IEEE Transactions on Emerging Topics in Computing 2025年

作者： Qiu, Houming Zhu, Kun Luong, Nguyen Cong Niyato, Dusit Jiangxi University of Finance and Economics School of Software and IoT Engineering Jiangxi 330032 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Phenikaa University Faculty of Computer Science Hanoi12116 Viet Nam Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

In a large-scale distributed machine learning system, coded computing has attracted wide-spread attention since it can effectively alleviate the impact of stragglers. However, several emerging problems greatly limit the performance of coded distributed systems. Firstly, an existence of colluding workers who collude results with each other leads to serious privacy leakage issues. Secondly, there are few existing works considering security issues in data transmission of distributed computing systems/or coded distributed machine learning systems. Thirdly, the number of required results for which need to wait increases with the degree of decoding functions. In this paper, we design a secure and private approximated coded distributed computing (SPACDC) scheme that deals with the above-mentioned problems simultaneously. Our SPACDC scheme guarantees data security during the transmission process using a new encryption algorithm based on elliptic curve cryptography. Especially, the SPACDC scheme does not impose strict constraints on the minimum number of results required to be waited for. An extensive performance analysis is conducted to demonstrate the effectiveness of our SPACDC scheme. Furthermore, we present a secure and private distributed learning algorithm based on the SPACDC scheme, which can provide information-theoretic privacy protection for training data. Our experiments show that the SPACDC-based deep learning algorithm achieves a significant speedup over the baseline approaches. © 2013 IEEE.

关键词： Parallel processing systems

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：