检索结果-内蒙古大学图书馆

Building Extraction From Multi-View RGB-H Images With General Instance Segmentation Networks and a Grouping Optimization Algorithm

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Yu, Dawen Cheng, Hao Fuzhou Univ Acad Digital China Key Lab Spatial Data Min & Informat Sharing Minist Educ Fuzhou 350108 Peoples R China Wuhan Univ Sch Remote Sensing Informat Engn Wuhan 430079 Peoples R China

Bird's-eye-view (BEV) building mapping from remote sensing images is a studying hotspot with broad applications. In recent years, deep learning (DL) has significantly advanced the development of automatic building extraction methods. However, most existing research focuses on segmenting buildings from a single perspective, such as orthophotos, overlooking the rich information of multi-view images. In surveying and mapping, individual building instances need to be separated even when they are adjacent or touching. Since orthophotos cannot capture building walls due to self-occlusion, distinguishing between closely connected buildings in densely built areas becomes challenging. To tackle this issue, we propose a multi-view collaborative pipeline for instance-level building segmentation. This pipeline utilizes a grouping optimization algorithm to merge segmentation results from multiple views, which are predicted by general instance segmentation networks and projected onto the BEV, to produce the final building instance polygons. Both qualitative and quantitative results show that the proposed multi-view collaborative pipeline significantly outperforms the popular orthophoto-based pipeline on the InstanceBuilding dataset.

关键词： Pipelines Buildings Instance segmentation Collaboration Image segmentation Optimization clustering algorithms Training Data mining Annotations Building extraction convolutional neural networks (CNNs) grouping optimization algorithm instance segmentation multi-view aerial images

来源：评论

学校读者我要写书评

暂无评论

The Core Cluster-Based Subspace Weighted clustering Ensemble

引用

WIRELESS COMMUNICATIONS & MOBILE COMPUTING 2022年第0期2022卷

作者： Huang, Xuan Qin, Fang Lin, Lin Univ Elect Sci & Technol China Chengdu Coll Chengdu 611731 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 610031 Peoples R China Dalian Univ Sci & Technol Sch Informat Sci & Technol Dalian 116052 Liaoning Peoples R China Chengdu Aeronaut Polytech Coll Informat Engn Chengdu 610100 Peoples R China

In recent years, the Internet of Things (IoT) technology has developed rapidly and is widely used in various fields. It is of great research significance to uncover underlying patterns and insights from the high-dimensional data of IoT, to excavate valuable information to guide people's production and life. clustering can explore the natural cluster structure of the data, which is conducive to further understanding of the data, and is an essential preprocessing step for data analysis. However, clustering is highly dependent on the data. In order to reduce the complexity of the model, reduce the computational cost, and obtain a more robust clustering solution, we combine subspace clustering and ensemble learning to propose a novel subspace weighted clustering ensemble framework for high-dimensional data. The proposed framework first combines random feature selection and unsupervised feature selection to generate a set of base subspaces. clustering is performed on each base subspace to achieve a set of subspace clustering solutions that generate a set of adaptive core clusters. The size of the core cluster is between the sample and the cluster. In the ensemble process, the core clusters are viewed as the basic unit, and the stability of the cluster is evaluated by measuring the distance between the core cluster pairs, and the similarity between the core clusters and the clusters in the base subspace, and then weighting the subspace clustering solution. Under this framework, we propose four subspace ensemble approaches based on core cluster to improve the accuracy of consensus clustering solutions. Extensive experiments are conducted on multiple real-world high-dimensional datasets, demonstrating that the proposed framework can process high-dimensional data for the IoT, and the proposed subspace clustering ensemble approaches are superior to the state-of-the-art clustering approaches.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Improving Address clustering in Bitcoin by Proposing Heuristics

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2022年第4期19卷 3737-3749页

作者： Zhao, Zening Wang, Jinsong Shi, Kai Zhang, Hongwei Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China

The Bitcoin system uses anonymous transactions to protect users' privacy, but attackers can use this defect of bitcoin transactions to discover the association between bitcoin addresses. At present, address clustering methods can make use of these vulnerabilities to associate the address as an entity to a certain extent. However, these address clustering methods have problems such as an insufficient inference rate of change addresses, inability to identify mixing transactions, and low efficiency of algorithm implementation. We propose some solutions to these problems. 1) We improve the method of change address identification to identify and mark more of them. 2) We propose a heuristic address clustering method related to mixing transactions, which can identify their privacy vulnerabilities. 3) We propose an incremental address clustering method that can store the historical state and more quickly discover the anonymity defect of Bitcoin. We use real Bitcoin transaction data to demonstrate our method's feasibility and reliability.

关键词： Bitcoin Privacy clustering methods clustering algorithms Inference algorithms Blockchains Symbols blockchain address clustering mixing services data privacy

来源：评论

学校读者我要写书评

暂无评论

Confidence-Based Simple Graph Convolutional Networks for Face clustering

引用

IEEE ACCESS 2022年 10卷 6459-6469页

作者： Sun, Dengdi Yang, Kang Ding, Zhuanlian Anhui Univ Sch Artificial Intelligence Minist Educ Key Lab Intelligent Comp & Signal Proc ICSP Hefei 230601 Peoples R China Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Comp Hefei 230601 Peoples R China Anhui Univ Sch Internet Hefei 230039 Peoples R China

Face clustering is an effective method for taking advantage of unlabeled face data. Recent studies use graph convolutional networks (GCNs) to learn feature embeddings from the neighborhood information between face images. However, most of the face clustering methods require numerous overlapping subgraphs to characterize the local structure around the nodes, which causes significant redundancy. Moreover, the nonlinearity of the GCN itself increases the calculation complexity, which further reduces the model's training efficiency. In this study, we propose a lightweight clustering framework, the confidence-based simple graph convolutional network (CSGCN), for face clustering, which achieves more accurate clustering results and significantly improves the efficiency of GCN-based face clustering. Specifically, CSGCN does not construct any subgraphs but convolves the entire graph as a whole and also removes the nonlinearity of the convolution in the graph convolution module, which further reduces the computational complexity. Subsequently, an effective new confidence score is constructed to better characterize the embedded features and to ensure that the subsequent clustering still maintains a high accuracy rate under the aforementioned model simplification. In addition, while most of the existing GCN-based methods are actually supervised, we construct an unsupervised confidence to make it more suitable for clustering tasks. Extensive experiments with MS-Celeb-1M, YouTube-Faces and DeepFashion datasets show that our method not only improves the clustering accuracy but also significantly reduces the execution time, whether in supervised or unsupervised models.

关键词： Faces Task analysis Convolution clustering algorithms Computational modeling clustering methods Training Face clustering confidence score simple graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral clustering for Unsupervised Segmentation in Videos

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第11期44卷 7638-7656页

作者： Haller, Emanuela Florea, Adina Magda Leordeanu, Marius Univ Politehn Bucuresti Bucharest 060042 Romania Bitdefender Bucharest 024102 Romania Romanian Acad Inst Math Bucharest 010702 Romania

We propose a dual system for unsupervised object segmentation in video, which brings together two modules with complementary properties: a space-time graph that discovers objects in videos and a deep network that learns powerful object features. The system uses an iterative knowledge exchange policy. A novel spectral space-time clustering process on the graph produces unsupervised segmentation masks passed to the network as pseudo-labels. The net learns to segment in single frames what the graph discovers in video and passes back to the graph strong image-level features that improve its node-level features in the next iteration. Knowledge is exchanged for several cycles until convergence. The graph has one node per each video pixel, but the object discovery is fast. It uses a novel power iteration algorithm computing the main space-time cluster as the principal eigenvector of a special Feature-Motion matrix without actually computing the matrix. The thorough experimental analysis validates our theoretical claims and proves the effectiveness of the cyclical knowledge exchange. We also perform experiments on the supervised scenario, incorporating features pretrained with human supervision. We achieve state-of-the-art level on unsupervised and supervised scenarios on four challenging datasets: DAVIS, SegTrack, YouTube-Objects, and DAVSOD. We will make our code publicly available.

关键词： Videos clustering algorithms Task analysis Object segmentation Mathematical models Deep learning Convergence Unsupervised video object segmentation spectral space-time clustering principal eigenvector power iteration space-time graph Feature-Motion matrix object discovery unsupervised learning deep learning

来源：评论

学校读者我要写书评

暂无评论

A Decoder-Free Variational Deep Embedding for Unsupervised clustering

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第10期33卷 5681-5693页

作者： Ji, Qiang Sun, Yanfeng Gao, Junbin Hu, Yongli Yin, Baocai Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Univ Sydney Business Sch Discipline Business Analyt Sydney NSW 2006 Australia

In deep clustering frameworks, autoencoder (AE)- or variational AE-based clustering approaches are the most popular and competitive ones that encourage the model to obtain suitable representations and avoid the tendency for degenerate solutions simultaneously. However, for the clustering task, the decoder for reconstructing the original input is usually useless when the model is finished training. The encoder-decoder architecture limits the depth of the encoder so that the learning capacity is reduced severely. In this article, we propose a decoder-free variational deep embedding for unsupervised clustering (DFVC). It is well known that minimizing reconstruction error amounts to maximizing a lower bound on the mutual information (MI) between the input and its representation. That provides a theoretical guarantee for us to discard the bloated decoder. Inspired by contrastive self-supervised learning, we can directly calculate or estimate the MI of the continuous variables. Specifically, we investigate unsupervised representation learning by simultaneously considering the MI estimation of continuous representations and the MI computation of categorical representations. By introducing the data augmentation technique, we incorporate the original input, the augmented input, and their high-level representations into the MI estimation framework to learn more discriminative representations. Instead of matching to a simple standard normal distribution adversarially, we use end-to-end learning to constrain the latent space to be cluster-friendly by applying the Gaussian mixture distribution as the prior. Extensive experiments on challenging data sets show that our model achieves higher performance over a wide range of state-of-the-art clustering approaches.

关键词： clustering algorithms Data models Neural networks Image reconstruction Decoding Training Estimation Augmented mutual information (MI) deep clustering self-supervised learning (SSL) variational embedding

来源：评论

学校读者我要写书评

暂无评论

Multigraph Random Walk for Joint Learning of Multiview clustering and Semisupervised Classification

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2022年第3期9卷 926-939页

作者： Wang, Shiping Fu, Lele Wang, Zhewen Xu, Haiping Zhu, William Univ Elect Sci & Technol China Inst Fundamental & Frontier Sci Chengdu 610054 Peoples R China Fuzhou Univ Coll Math & Comp Sci Fuzhou 350108 Peoples R China Minjiang Univ Coll Math & Data Sci Fuzhou 350108 Peoples R China

Recent researches on multiview learning have received widespread attention due to the increasing generalization of multiview data. As an effective probabilistic model, random walk has also shown encouraging performance in various fields. To further exploit the potential of utilizing random walk schemes to address multiview learning problems, this article proposes a simple yet efficient multigraph random walk scheme for both multiview clustering and semisupervised classification tasks. The proposed model integrates random walk with multiview learning, and recursively learns a globally stable probability distribution matrix from multiple views, on the basis of which the label indicator is obtained in the scene of clustering or semisupervised classification. Furthermore, an adaptive weight vector is learned to incorporate the diversity and complementarity of multiview data. Besides, the relationships between the proposed scheme and spectral clustering, neighborhood embedding and manifold embedding are analyzed theoretically. Finally, comprehensive comparative experiments are conducted with several state-of-the-art multiview clustering and semisupervised classification methods on eight real-world datasets. The experimental results demonstrate the superiority of the proposed method in terms of both clustering and classification performance.

关键词： Task analysis Correlation clustering algorithms Probability distribution Mathematical model Analytical models Tensors Multigraph multimodal fusion multiview clustering random walk semisupervised classification

来源：评论

学校读者我要写书评

暂无评论

Multiview Subspace clustering Based on Adaptive Global Affinity Graph Learning

引用

JOURNAL OF COMPUTER AND SYSTEMS SCIENCES INTERNATIONAL 2022年第1期61卷 24-37页

作者： Chen, X. Zhu, D. Wang, L. Zhu, Y. Matveev, I. A. Nanjing Univ Aeronaut & Astronaut Sci Coll Nanjing Peoples R China Nanjing Univ Aeronaut & Astronaut Lab Math Modeling & High Performance Comp Aircraf Nanjing Peoples R China Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia Nanjing Univ Aeronaut & Astronaut Fac Expt Teaching Nanjing Peoples R China

Multiview subspace clustering is a hot topic in machine learning. Most existing methods perform clustering based on a predefined affinity graph constructed from the neighbor information of the data., which affects the performance of clustering greatly. A method is proposed to solve this problem by constructing adjacency graphs in each of the feature spaces and a common object affinity graph. A sequence of iterations is performed, at each of which the adjacency graphs and the affinity graph are refined. A restriction is also imposed on the rank of the Laplace matrix of the affinity graph, which, according to a well-known theorem, ensures the partition of the graph into several connected components, which, after the completion of the iterations, are considered the required clusters. In the numerical experiments, several test bases from open sources are used. The results are compared with the known methods, and some advantage of the proposed approach is obtained.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

On a New Rough clustering Based on Optimization 13

On a New Rough Clustering Based on Optimization

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Furuta, Sakuya Endo, Yasunori Master's Program in Risk and Resilience Engineering Degree Programs in Systems and Information Engineering Graduate School of Science Annd Technology University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki305-8573 Japan Institute of Systems and Information Engineering University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki305-8573 Japan

ISBN: (纸本)9798350373332

The purpose of this study is to develop and investigate a new rough clustering based on optimization. We propose a restructured algorithm using only one variable, instead of the algorithm described using two variables in existing methods. We also perform numerical examples using artificial data and the Iris and Wine datasets. This research has the potential to be used as a method for determining false negatives and false positives in cancer diagnosis. © 2024 IEEE.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Integrating Tensor Similarity to Enhance clustering Performance

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第5期44卷 2582-2593页

作者： Peng, Hong Hu, Yu Chen, Jiazhou Wang, Haiyan Li, Yang Cai, Hongmin South China Univ Technol Sch Comp Sci & Engn Guangzhou 510641 Guangdong Peoples R China

The performance of most clustering methods hinges on the used pairwise affinity, which is usually denoted by a similarity matrix. However, the pairwise similarity is notoriously known for its vulnerability of noise contamination or the imbalance in samples or features, and thus hinders accurate clustering. To tackle this issue, we propose to use information among samples to boost the clustering performance. We proved that a simplified similarity for pairs, denoted by a fourth order tensor, equals to the Kronecker product of pairwise similarity matrices under decomposable assumption, or provide complementary information for which the pairwise similarity missed under indecomposable assumption. Then a high order similarity matrix is obtained from the tensor similarity via eigenvalue decomposition. The high order similarity capturing spatial information serves as a robust complement for the pairwise similarity. It is further integrated with the popular pairwise similarity, named by IPS2, to boost the clustering performance. Extensive experiments demonstrated that the proposed IPS2 significantly outperformed previous similarity-based methods on real-world datasets and it was capable of handling the clustering task over under-sampled and noisy datasets.

关键词： Tensors Matrix decomposition Laplace equations clustering algorithms Task analysis Noise measurement Manifolds Tensor similarity kronecker product spectral clustering under-sampled imbalanced dataset unsupervised 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：