检索结果-南通市图书馆

Active label distribution learning via kernel maximum mean discrepancy

Frontiers of Computer Science 2023年第4期17卷 69-81页

作者： Xinyue DONG Tingjin LUO Ruidong FAN Wenzhang ZHUGE Chenping HOU College of Science National University of Defense TechnologyChangsha 410073China

Label distribution learning(LDL)is a new learning paradigm to deal with label ambiguity and many researches have achieved the prominent *** with traditional supervised learning scenarios,the annotation with label distribution is more *** use of existing active learning(AL)approaches,which aim to reduce the annotation cost in traditional learning,may lead to the degradation of their *** deal with the problem of high annotation cost in LDL,we propose the active label distribution learning via kernel maximum mean discrepancy(ALDL-kMMD)method to tackle this crucial but rarely studied ***-kMMD captures the structural information of both data and label,extracts the most representative instances from the unlabeled ones by incorporating the nonlinear model and marginal probability distribution ***,it is also able to markedly decrease the amount of queried unlabeled ***,an effective solution is proposed for the original optimization problem of ALDL-kMMD by constructing auxiliary *** effectiveness of our method is validated with experiments on the real-world datasets.

关键词： label distribution learning active learning maximum mean discrepancy auxiliary variable

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Knowledge Transfer Learning via Dual Density Sampling for Resource-Limited Domain Adaptation

引用

IEEE/CAA Journal of Automatica Sinica 2023年第12期10卷 2269-2291页

作者： Zefeng Zheng Luyao Teng Wei Zhang Naiqi Wu Shaohua Teng the School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China the School of Information Engineering Guangzhou Panyu PolytechicGuangzhou 511483China the Faculty of Information Technology Monash University20 Exhibition Walk ClaytonVIC 3800Australia IEEE the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems Macao University of Science and TechnologyMacao 999078China

Most existing domain adaptation(DA) methods aim to explore favorable performance under complicated environments by ***,there are three unsolved problems that limit their efficiencies:ⅰ) they adopt global sampling but neglect to exploit global and local sampling simultaneously;ⅱ)they either transfer knowledge from a global perspective or a local perspective,while overlooking transmission of confident knowledge from both perspectives;and ⅲ) they apply repeated sampling during iteration,which takes a lot of *** address these problems,knowledge transfer learning via dual density sampling(KTL-DDS) is proposed in this study,which consists of three parts:ⅰ) Dual density sampling(DDS) that jointly leverages two sampling methods associated with different views,i.e.,global density sampling that extracts representative samples with the most common features and local density sampling that selects representative samples with critical boundary information;ⅱ)Consistent maximum mean discrepancy(CMMD) that reduces intra-and cross-domain risks and guarantees high consistency of knowledge by shortening the distances of every two subsets among the four subsets collected by DDS;and ⅲ) Knowledge dissemination(KD) that transmits confident and consistent knowledge from the representative target samples with global and local properties to the whole target domain by preserving the neighboring relationships of the target *** analyses show that DDS avoids repeated sampling during the *** the above three actions,confident knowledge with both global and local properties is transferred,and the memory and running time are greatly *** addition,a general framework named dual density sampling approximation(DDSA) is extended,which can be easily applied to other DA *** experiments on five datasets in clean,label corruption(LC),feature missing(FM),and LC&FM environments demonstrate the encouraging performance of KTL-DDS.

关键词： Cross-domain risk dual density sampling intra-domain risk maximum mean discrepancy knowledge transfer learning resource-limited domain adaptation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Enhancing Unsupervised Domain Adaptation for Person Re-Identification with the Minimal Transfer Cost Framework

引用

Computers, Materials & Continua 2024年第9期80卷 4197-4218页

作者： Sheng Xu Shixiong Xiang Feiyu Meng Qiang Wu Research Institute of Electronic Science and Technology University of Electronic Science and Technology of ChinaChengdu610000China National Key Laboratory of Optical FieldManipulation Science and Technology Chinese Academy of SciencesChengdu610209China

In Unsupervised Domain Adaptation(UDA)for person re-identification(re-ID),the primary challenge is reducing the distribution discrepancy between the source and target *** can be achieved by implicitly or explicitly constructing an appropriate intermediate domain to enhance recognition capability on the target *** construction is difficult due to the absence of intermediate state supervision,making smooth knowledge transfer from the source to the target domain a *** explicitly construct the most suitable intermediate domain for the model to gradually adapt to the feature distribution changes from the source to the target domain,we propose the Minimal Transfer Cost Framework(MTCF).MTCF considers all scenarios of the intermediate domain during the transfer process,ensuring smoother and more efficient domain *** framework mainly includes threemodules:Intermediate Domain Generator(IDG),Cross-domain Feature Constraint Module(CFCM),and Residual Channel Space Module(RCSM).First,the IDG Module is introduced to generate all possible intermediate domains,ensuring a smooth transition of knowledge fromthe source to the target *** reduce the cross-domain feature distribution discrepancy,we propose the CFCM Module,which quantifies the difficulty of knowledge transfer and ensures the diversity of intermediate domain features and their semantic relevance,achieving alignment between the source and target domains by incorporating mutual information and maximum mean *** also design the RCSM,which utilizes attention mechanism to enhance the model’s focus on personnel features in low-resolution images,improving the accuracy and efficiency of person *** proposed method outperforms existing technologies in all common UDA re-ID tasks and improves the mean Average Precision(mAP)by 2.3%in the Market to Duke task compared to the state-of-the-art(SOTA)methods.

关键词： Person re-identification unsupervised domain adaptation attention mechanism mutual information maximum mean discrepancy

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Enhanced vision-transformer integrating with semi-supervised transfer learning for state of health and remaining useful life estimation of lithium-ion batteries

Energy and AI

引用

Energy and AI 2024年第3期17卷 380-396页

作者： Ya-Xiong Wang Shangyu Zhao Shiquan Wang Kai Ou Jiujun Zhang School of Mechanical Engineering and Automation Fuzhou UniversityFuzhou 350108China College of Materials Science and Engineering Fuzhou UniversityFuzhou 350108China

The state of health(SOH)and remaining useful life(RUL)of lithium-ion batteries are crucial for health management and ***,most data-driven estimation methods heavily rely on scarce labeled data,while traditional transfer learning faces challenges in handling domain shifts across various battery *** paper proposes an enhanced vision-transformer integrating with semi-supervised transfer learning for SOH and RUL estimation of lithium-ion batteries.A depth-wise separable convolutional vision-transformer is developed to extract local aging details with depth-wise convolutions and establishes global dependencies between aging information using multi-head *** mean discrepancy is employed to initially reduce the distribution difference between the source and target domains,providing a superior starting point for fine-tuning the target domain ***,the abundant aging data of the same type as the target battery are labeled through semi-supervised learning,compensating for the source model's limitations in capturing target battery aging *** regularization incorporates the cross-entropy between predictions with and without adversarial perturbations into the gradient backpropagation of the overall *** particular,across the experimental groups 13–15 for different types of batteries,the root mean square error of SOH estimation was less than 0.66%,and the mean relative error of RUL estimation was 3.86%.Leveraging extensive unlabeled aging data,the proposed method could achieve accurate estimation of SOH and RUL.

关键词： State of health(S0H) Remaining useful life(RUL) Depth-wise separable convolutional vision-transformer Transfer learning maximum mean discrepancy Semi supervised learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A kernel learning framework for domain adaptation learning

引用

Science China(Information Sciences) 2012年第9期55卷 1983-2007页

作者： TAO JianWen 1,3,CHUNG FuLai 2 & WANG ShiTong 1,2 1 School of Digital Media,Jiangnan University,Wuxi 214122,China 2 Department of Computing,Hong Kong Polytechnic University,Hong Kong,China 3 School of Information Engineering,Zhejiang Business Technology Institute,Ningbo 315012,China School of Digital Media Jiangnan University Wuxi China School of Information Engineering Zhejiang Business Technology Institute Ningbo China Department of Computing Hong Kong Polytechnic University Hong Kong China

Domain adaptation learning(DAL) methods have shown promising results by utilizing labeled samples from the source(or auxiliary) domain(s) to learn a robust classifier for the target domain which has a few or even no labeled ***,there exist several key issues which need to be addressed in the state-of-theart DAL methods such as sufficient and effective distribution discrepancy metric learning,effective kernel space learning,and multiple source domains transfer learning,*** at the mentioned-above issues,in this paper,we propose a unified kernel learning framework for domain adaptation learning and its effective extension based on multiple kernel learning(MKL) schema,regularized by the proposed new minimum distribution distance metric criterion which minimizes both the distribution mean discrepancy and the distribution scatter discrepancy between source and target domains,into which many existing kernel methods(like support vector machine(SVM),v-SVM,and least-square SVM) can be readily *** framework,referred to as kernel learning for domain adaptation learning(KLDAL),simultaneously learns an optimal kernel space and a robust classifier by minimizing both the structural risk functional and the distribution discrepancy between different ***,we extend the framework KLDAL to multiple kernel learning framework referred to as *** the KLDAL or MKLDAL framework,we also propose three effective formulations called KLDAL-SVM or MKLDAL-SVM with respect to SVM and its variant μ-KLDALSVM or μ-MKLDALSVM with respect to v-SVM,and KLDAL-LSSVM or MKLDAL-LSSVM with respect to the least-square SVM,*** experiments on real-world data sets verify the outperformed or comparable effectiveness of the proposed frameworks.

关键词： domain adaptation learning support vector machine multiple kernel learning maximum mean discrepancy maximum scatter discrepancy

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Generative Adversarial Networks with Joint Distribution Moment Matching

引用

Journal of the Operations Research Society of China 2019年第4期7卷 579-597页

作者： Yi-Ying Zhang Chao-Min Shen Hao Feng Preston Thomas Fletcher Gui-Xu Zhang Department of Computer Science East China Normal UniversityShanghai 200062China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal UniversityShanghai 200062China Westlake Institute for Brain-Like Science and Technology Hangzhou 310027China Didi Chuxing Science and Technology Co.Ltd. Beijing 100193China Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904USA

Generative adversarial networks(GANs)have shown impressive power in the field of machine *** GANs have focused on unsupervised learning *** recent years,conditional GANs that can generate data with labels have been proposed in semi-supervised learning and have achieved better image quality than traditional *** GANs,however,generally only minimize the difference between marginal distributions of real and generated data,neglecting the difference with respect to each class of the *** address this challenge,we propose the GAN with joint distribution moment matching(JDMM-GAN)for matching the joint distribution based on maximum mean discrepancy,which minimizes the differences of both the marginal and conditional *** learning procedure is iteratively conducted by the stochastic gradient descent and *** evaluate JDMM-GAN on several benchmark datasets,including MNIST,CIFAR-10 and the Extended Yale *** with the state-of-the-art GANs,JDMM-GAN generates more realistic images and achieves the best inception score for CIFAR-10 dataset.

关键词： Generative Adversarial Networks Joint Distribution Moment Matching maximum mean discrepancy

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation with Multi-kernel MMD

Unsupervised Domain Adaptation with Multi-kernel MMD

引用

第40届中国控制会议

作者： Juntao Huang Hongsheng Qi School of Mathematical Sciences University of Chinese Academy of Sciences Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of Sciences

In this work,we propose a method to solve the problem of unsupervised domain *** of existing works are based on adversarial learning method,which obtains the features of inputs through a feature extraction network,and distinguishes the features by a domain classifier that can generate domain-invariant *** domain-invariant features is used as the input of a classifier（fully connected network） to get the final category of the ***,in fact,each layer of the fully connected network can be regarded as the domain invariant ***,we employ the last layer as domain-invariant features which can also be considered as a probability ***,the domain discrepancies between the distribution in source domain and target domain is measured by multi-kernel MMD,which is what we need to *** evidences show that the proposed method achieves satisfactory results on standard domain adapatation benchmarks.

关键词： Unsupervised Domain Adapatation maximum mean discrepancy

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：