检索结果-内蒙古大学图书馆

A Spectral Clustering on Grassmann Manifold via Double Low Rank Constraint

学校读者我要写书评

暂无评论

A Spectral Clustering on Grassmann Manifold via Double Low R...

International Conference on Pattern Recognition

作者： Xinglin Piao Yongli Hu Junbin Gao Yanfeng Sun Xin Yang Baocai Yin Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian China Faculty of Information Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Artificial Intelligence Institute Beijing University of Technology Beijing China Business Analytics Discipline The University of Sydney Business School Camperdown NSW Australia

Data clustering is a fundamental topic in machine learning and data mining areas. In recent years, researchers have proposed a series of effective methods based on Low Rank Representation (LRR) which could explore low-dimension subspace structure embedded in original data effectively. The traditional LRR methods usually are designed for vectorial data from linear spaces with Euclidean distance. However, high-dimension data (such as video clip or imageset) are always considered as non-linear manifold data such as Grassmann manifold with non-linear metric. In addition, traditional LRR clustering method always adopt single nuclear norm as low rank constraint which would lead to suboptimal solution and decrease the clustering accuracy. In this paper, we proposed a new low rank method on Grassmann manifold for video or imageset data clustering task. In the proposed method, video or imageset data are formulated as sample data on Grassmann manifold first. And then a double low rank constraint is proposed by combining the nuclear norm and bilinear representation for better construct the representation matrix. The experimental results on several public datasets show that the proposed method outperforms the state-of-the-art clustering methods.

关键词： Manifolds Measurement Clustering methods Machine learning Euclidean distance Data models Data mining

Unravelling spontaneous Bloch-type skyrmion in centrosymmetric two-dimensional magnets

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pang, Jingman Niu, Xiaohang Zhao, Hong Jian Zhang, Yun Bellaiche, Laurent College of Physics and Optoelectronic Technology Collaborative Innovation Center of Rare-Earth Functional Materials and Devices Development Baoji University of Arts and Sciences Baoji721016 China Faculty of Chemistry and Chemical Engineering Baoji University of Arts and Sciences 1 Hi-Tech Avenue Shaanxi Baoji China Key Laboratory of Material Simulation Methods and Software of Ministry of Education College of Physics Jilin University Changchun130012 China Physics Department Institute for Nanoscience and Engineering University of Arkansas FayettevilleAR72701 United States

The realization of magnetic skyrmions in two-dimensional (2D) magnets holds great promise for both fundamental research and device applications. Despite recent progress, two-dimensional skyrmions hosts are still limited, due to the fact that most 2D magnets are centrosymmetric and thus lack Dzyaloshinskii−Moriya interaction (DMI). We show here, using a general analysis based on symmetry, that Bloch-type skyrmions can, in fact, be stabilized in 2D magnets, due to the interplay between in-plane component (dx) of second nearest-neighbor DMI and magnetic anisotropy. Its validity is demonstrated in Cr2Ge2Te6 monolayer, which is also verified by recent experiments. Our work gives a clear direction for experimental studies of 2D magnetic materials to stabilize skyrmions and should greatly enrich the research on magnetic skyrmions in 2D lattices. © 2023, CC BY.

关键词： Magnetic anisotropy

Towards Generalization and Data Efficient Learning of Deep Robotic Grasping

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Zhixin Lin, Mengxiang Jia, Zhixin Jian, Shibo State Key Laboratory of Software Development Environment School of Mechanical Engineering and Automation Beihang University Beijing China

—Deep reinforcement learning (DRL) has been proven to be a powerful paradigm for learning complex control policy autonomously. Numerous recent applications of DRL in robotic grasping have successfully trained DRL robotic agents end-to-end, mapping visual inputs into control instructions directly, but the amount of training data required may hinder these applications in practice. In this paper, we propose a DRL based robotic visual grasping framework, in which visual perception and control policy are trained separately rather than end-to-end. The visual perception produces physical descriptions of grasped objects and the policy takes use of them to decide optimal actions based on DRL. Benefiting from the explicit representation of objects, the policy is expected to be endowed with more generalization power over new objects and environments. In addition, the policy can be trained in simulation and transferred in real robotic system without any further training. We evaluate our framework in a real world robotic system on a number of robotic grasping tasks, such as semantic grasping, clustered object grasping, moving object grasping. The results show impressive robustness and generalization of our system. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Entity concept-enhanced few-shot relation extraction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Shan Zhang, Yongfei Niu, Guanglin Zhao, Qinhua Pu, Shiliang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering BeiHang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing100191 China Pengcheng Laboratory Shenzhen518055 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering BeiHang University Beijing100191 China Hikvision Research Institute Hangzhou311500 China

Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data. Most existing FSRE algorithms fail to accurately classify the relations merely based on the information of the sentences together with the recognized entity pairs, due to limited samples and lack of knowledge. To address this problem, in this paper, we proposed a novel entity CONCEPTenhanced FEw-shot Relation Extraction scheme (ConceptFERE), which introduces the inherent concepts of entities to provide clues for relation prediction and boost the relations classification performance. Firstly, a conceptsentence attention module is developed to select the most appropriate concept from multiple concepts of each entity by calculating the semantic similarity between sentences and concepts. Secondly, a self-attention based fusion module is presented to bridge the gap of concept embedding and sentence embedding from different semantic spaces. Extensive experiments on the FSRE benchmark dataset FewRel have demonstrated the effectiveness and the superiority of the proposed ConceptFERE scheme as compared to the state-of-the-art baselines. Code is available at https://***/LittleGuoKe/ConceptFERE. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Wireless Large AI Model: Shaping the AI-Native Future of 6G and Beyond

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhu, Fenghao Wang, Xinquan Li, Xinyi Zhang, Maojun Chen, Yixuan Huang, Chongwen Yang, Zhaohui Chen, Xiaoming Zhang, Zhaoyang Jin, Richeng Huang, Yongming Feng, Wei Yang, Tingting Bai, Baoming Gao, Feifei Yang, Kun Liu, Yuanwen Muhaidat, Sami Yuen, Chau Huang, Kaibin Wong, Kai-Kit Niyato, Dusit Debbah, Mérouane College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China School of Automation Southeast University Nanjing210096 China Tsinghua University Beijing100084 China Pengcheng Laboratory Shenzhen518066 China State Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China State Key Laboratory of Novel Software Technology Nanjing University Nanjing210008 China Suzhou215163 China The University of Hong Kong Hong Kong KU 6G Research Center Computer and Communication Engineering Khalifa University Abu Dhabi127788 United Arab Emirates School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Department of Electronic and Electrical Engineering University College London LondonWC1E 7JE United Kingdom College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore KU 6G Research Center Department of Computer and Information Engineering Khalifa University Abu Dhabi127788 United Arab Emirates

The emergence of sixth-generation and beyond communication systems is expected to fundamentally transform digital experiences through introducing unparalleled levels of intelligence, efficiency, and connectivity. A promising technology poised to enable this revolutionary vision is the wireless large AI model (WLAM), characterized by its exceptional capabilities in data processing, inference, and decision-making. In light of these remarkable capabilities, this paper provides a comprehensive survey of WLAM, elucidating its fundamental principles, diverse applications, critical challenges, and future research opportunities. We begin by introducing the background of WLAM and analyzing the key synergies with wireless networks, emphasizing the mutual benefits. Subsequently, we explore the foundational characteristics of WLAM, delving into their unique relevance in wireless environments. Then, the role of WLAM in optimizing wireless communication systems across various use cases and the reciprocal benefits are systematically investigated. Furthermore, we discuss the integration of WLAM with emerging technologies, highlighting their potential to enable transformative capabilities and breakthroughs in wireless communication. Finally, we thoroughly examine the high-level challenges hindering the practical implementation of WLAM and discuss pivotal future research directions. Copyright © 2025, The Authors. All rights reserved.

关键词： Sorting

Single-path Bit Sharing for Automatic Loss-aware Model Compression

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jing Zhuang, Bohan Chen, Peng Shen, Chunhua Cai, Jianfei Tan, Mingkui The School of Software Engineering South China University of Technology China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China The School of Computer Science the University of Adelaide Australia The Faculty of Information Technology Monash University Australia The College of Computer Science and Technology Zhejiang University Hangzhou China

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct quantization based on the pruned model. However, this strategy may ignore that the pruning and quantization would affect each other and thus performing them separately may lead to sub-optimal performance. To address this, performing pruning and quantization jointly is essential. Nevertheless, how to make a trade-off between pruning and quantization is non-trivial. Moreover, existing compression methods often rely on some pre-defined compression configurations (i.e., pruning rates or bitwidths). Some attempts have been made to search for optimal configurations, which however may take unbearable optimization cost. To address these issues, we devise a simple yet effective method named Single-path Bit Sharing (SBS) for automatic loss-aware model compression. To this end, we consider the network pruning as a special case of quantization and provide a unified view for model pruning and quantization. We then introduce a single-path model to encode all candidate compression configurations, where a high bitwidth value will be decomposed into the sum of a lowest bitwidth value and a series of re-assignment offsets. Relying on the single-path model, we introduce learnable binary gates to encode the choice of configurations and learn the binary gates and model parameters jointly. More importantly, the configuration search problem can be transformed into a subset selection problem, which helps to significantly reduce the optimization difficulty and computation cost. In this way, the compression configurations of each layer and the trade-off between pruning and quantization can be automatically determined. Extensive experiments on CIFAR-100 and ImageNet show that SBS significantly reduces computation cost while achieving promising performance. For example, our SBS compressed MobileNetV2 achieves

关键词： Encoding (symbols)

Gathering GitHub OSS Requirements from Q&A Community: an Empirical Study

学校读者我要写书评

暂无评论

Gathering GitHub OSS Requirements from Q&A Community: an Emp...

IEEE International Conference on engineering of Complex Computer Systems

作者： Hao Huang Yao Lu Xinjun Mao Key Laboratory of Software Engineering for Complex Systems College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9781728185583

ISBN: (纸本)9781728185590

Cross-community collaboration can exploit the expertise and knowledges of crowds in different communities. Recently increasing users in open source software (OSS) community like GitHub attempt to gather software requirements from question and answer (Q&A) communities such as Stack Overflow (SO). In order to investigate this emerging cross-community collaboration phenomenon, the paper presents an exploratory study on cross-community requirements gathering of OSS projects in GitHub. We manually sample 3266 practice cases and quantitatively analyze the popularity of the phenomenon, the characteristics of the gathered requirements, and cross-community collaboration behaviors of users. Some important findings are obtained: more than half of the requirements gathered from SO are enhancements and the majority of the gathered requirements are non-functional requirements. In addition, OSS developers can directly obtain related solutions and contributions of the gathered requirements from SO in the gathering process.

关键词： Collaboration Manuals Tools software Time factors Open source software software development management

Research on Automatic Online Analysis Method of Data Hotness in Big Data Scenario

学校读者我要写书评

暂无评论

Research on Automatic Online Analysis Method of Data Hotness...

International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)

作者： Jiahao Xu Ying Song Bo Wang Beijing Key Laboratory of Internet Culture and Digital Dissemination Research Beijing Advanced Innovation Center for Materials Genome Engineering Beijing Information Science and Technology University Beijing China Software Engineering College Zhengzhou University of Light Industry Zhengzhou China

ISBN: (纸本)9781665417914

With the development of Big Data technology, data volume has reached a massive level, and the types of data have become more complex, while the access characteristics of data by different applications vary widely, resulting in significant differences in the frequency of different data being accessed. In order to efficiently manage massive amounts of data, more and more data management and deployment systems are considering policies based on the hotness of data access. Therefore, how to define the hotness of data and extract the hotness of data online becomes a pressing problem nowadays. To address this problem, this paper proposes an online method to calculate data hotness, which takes into account both the creation time of data (called age in this paper) and the frequency of data access. In order to verify the above method, this paper focuses on the application scenario of Amazon product review data analysis. Through analyzing the review data on HDFS cluster, the universality of different hotness data distribution of HDFS cluster is verified, and it shows better advantages by comparing with other work.

关键词： Heating systems Time-frequency analysis Pressing Machine learning Big Data applications Data mining Business intelligence

LF-YOLO: A lighter and faster yolo for weld defect detection of X-ray image

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Moyun Chen, Youping He, Lei Zhang, Yang Xie, Jingming The School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China The School of Mechanical Engineering Hubei University of Technology Wuhan430068 China The National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

X-ray image plays an important role in manufacturing industry for quality assurance, because it can reflect the internal condition of weld region. However, the shape and scale of different defect types vary greatly, which makes it challenging for model to detect weld defects. In this paper, we propose a weld defect detection method based on convolution neural network, namely Lighter and Faster YOLO (LF-YOLO). In particularly, a reinforced multiscale feature (RMF) module is designed to implement both parameter-based and parameter-free multi-scale information extracting operation. RMF enables the extracted feature map capable to represent more plentiful information, which is achieved by superior hierarchical fusion structure. To improve the performance of detection network, we propose an efficient feature extraction (EFE) module. EFE processes input data with extremely low consumption, and improves the practicability of whole network in actual industry. Experimental results show that our weld defect detection network achieves satisfactory balance between performance and consumption, and reaches 92.9 mean average precision (mAP50) with 61.5 frames per second (FPS). To further prove the ability of our method, we test it on public dataset MS COCO, and the results show that our LF-YOLO has a outstanding versatility detection performance. The code is available at https://***/lmomoy/LF-YOLO. © 2021, CC BY.

关键词： Feature extraction