检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Ziyi Zhang Weikai Chen Hui Cheng Zhen Li Siyuan Li Liang Lin Guanbin Li National Key Laboratory of Novel Software Technology Nanjing University Nanjing China Tencent America School of Computer Science and Engineering Sun Yat-sen University Guangzhou China The Chinese University of Hong Kong Shenzhen China and Shenzhen Research Institute of Big Data Shenzhen China AI Lab School of Engineering Westlake University Hangzhou China

ISBN: (纸本)9781713871088

We investigate a practical domain adaptation task, called source-free unsupervised domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages the feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks - the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from the source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the sourcelike domain with the target-specific samples using a memory-based maximum mean discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects

arXiv

引用

arXiv 2023年

作者： Wang, Jiapu Wang, Boyue Qiu, Meikang Pan, Shirui Xiong, Bo Liu, Heng Luo, Linhao Liu, Tengfei Hu, Yongli Yin, Baocai Gao, Wen Beijing Municipal Key Lab of Multimedia and Intelligent Software Technology Beijing Artificial Intelligence Institute Faculty of Information Technology Beijing University of Technology Beijing100124 China The Beacom College of Computer and Cyber Sciences Dakota State University MadisonSD United States Griffith University QLD Australia The Department of Computer Science University of Stuttgart Stuttgart70569 Germany The Department of Data Science and AI Monash University Melbourne Australia The Institute of Digital Media Peking University Beijing100871 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China

Temporal characteristics are prominently evident in a substantial volume of knowledge, which underscores the pivotal role of Temporal Knowledge Graphs (TKGs) in both academia and industry. However, TKGs often suffer from incompleteness for three main reasons: the continuous emergence of new knowledge, the weakness of the algorithm for extracting structured information from unstructured data, and the lack of information in the source dataset. Thus, the task of Temporal Knowledge Graph Completion (TKGC) has attracted increasing attention, aiming to predict missing items based on the available information. In this paper, we provide a comprehensive review of TKGC methods and their details. Specifically, this paper mainly consists of three components, namely, 1) Background, which covers the preliminaries of TKGC methods, loss functions required for training, as well as the dataset and evaluation protocol;2) Interpolation, that estimates and predicts the missing elements or set of elements through the relevant available information. It further categorizes related TKGC methods based on how to process temporal information;3) Extrapolation, which typically focuses on continuous TKGs and predicts future events, and then classifies all extrapolation methods based on the algorithms they utilize. We further pinpoint the challenges and discuss future research directions of TKGC. Copyright © 2023, The Authors. All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Approximate equivalence checking of noisy quantum circuits

arXiv

引用

arXiv 2021年

作者： Hong, Xin Ying, Mingsheng Feng, Yuan Zhou, Xiangzhen Li, Sanjiang Centre for Quantum Software and Information University of Technology Sydney Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Department of Computer Science and Technology Tsinghua University China State Key Lab of Millimeter Waves Southeast University China

We study the fundamental design automation problem of equivalence checking in the NISQ (Noisy Intermediate-Scale Quantum) computing realm where quantum noise is present inevitably. The notion of approximate equivalence of (possibly noisy) quantum circuits is defined based on the Jamiolkowski fidelity which measures the average distance between output states of two super-operators when the input is chosen at random. By employing tensor network contraction, we present two algorithms, aiming at different situations where the number of noises varies, for computing the fidelity between an ideal quantum circuit and its noisy implementation. The effectiveness of our algorithms is demonstrated by experimenting on benchmarks of real NISQ circuits. When compared with the state-of-the-art implementation incorporated in Qiskit, experimental results show that the proposed algorithms outperform in both efficiency and scalability. Copyright © 2021, The Authors. All rights reserved.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

SoLar: sinkhorn label refinery for imbalanced partial-label learning 22

SoLar: sinkhorn label refinery for imbalanced partial-label ...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Haobo Wang Mingxuan Xia Yixuan Li Yuren Mao Lei Feng Gang Chen Junbo Zhao Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University School of Software Technology Zhejiang University Department of Computer Sciences University of Wisconsin-Madison College of Computer Science Chongqing University and Center for Advanced Intelligence Project RIKEN

ISBN: (纸本)9781713871088

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior work failed. We subsequently propose SoLar, a novel Optimal Transport-based framework that allows to refine the disambiguated labels towards matching the marginal class prior distribution. SoLar additionally incorporates a new and systematic mechanism for estimating the long-tailed class prior distribution under the PLL setup. Through extensive experiments, SoLar exhibits substantially superior results on standardized benchmarks compared to the previous state-of-the-art PLL methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uplink Control Information Based Clustered Access and Discontinuous Reception Management for mMTC

引用

IEEE Communications Letters 2025年第6期29卷 1380-1384页

作者： Wang, Shao-Di Wang, Chang-Long Wang, Hui-Ming Zhou, Feng Leung, Victor C. M. Xidian University Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education Xi’an710071 China Xi’an Jiaotong University School of Information and Communication Engineering Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an710049 China Shenzhen MSU BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Uplink control information (UCI) and discontinuous reception (DRX) play important roles for massive machine type communication (mMTC). Despite their standalone significance, a conspicuous gap exists in comprehensively exploring the synergy between UCI and DRX concerning both energy conservation and latency reduction for mMTC. In this letter, we propose a UCI-based clustered access and DRX management (UCADM) scheme that strikes a balance between these two critical performance metrics, reducing energy usage while preserving low latency in uplink-downlink interaction for mMTC. Specifically, we present a strictly feasible solution for the proposed UCADM scheme by using the spectral radius and the constraint projection, which can effectively solve DRX switching operations as indicated by scheduling information from UCI. Simulation results confirm the effectiveness of our scheme. © 1997-2012 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

arXiv

引用

arXiv 2022年

作者： Zhou, Haoran Chen, Honghua Zhang, Yingkui Wei, Mingqiang Xie, Haoran Wang, Jun Lu, Tong Qin, Jing Zhang, Xiao-Ping State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China Department of Computing and Decision Sciences Lingnan University Hong Kong School of Nursing The Hong Kong Polytechnic University Hong Kong Department of Electrical Computer and Biomedical Engineering Ryerson University Toronto Canada

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets. Our code is available at https://***/hrzhou2/refinenet. Copyright © 2022, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Low-Speed Injection Attack Detection on CAN Bus 3rd

Low-Speed Injection Attack Detection on CAN Bus

引用

3rd International Conference on Frontiers in Cyber Security, FCS 2020

作者： Wang, Chundong Li, Chuang An, Tongle Cheng, Xiaochun Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Ministry of Education Tianjin University of Technology Tianjin300384 China Department of Computer Science Middlesex University LondonNW4 4BT United Kingdom

ISBN: (纸本)9789811597381

The car CAN (Controller Area Network) bus message injection attacks seriously affects various functions of the safety of cars, life and property. However, low-speed injection attack is detection inconspicuous in a majority of existing researches. This paper proposes a self-contained low-speed injection attacks detection system including whole detection process and principle. This paper first analyzes the feasibility of low-speed injection attacks;then we propose to use LOF (Local Outlier Factor) to detect the injection attack, and compare with the previous detection algorithms. Experimental results show that our algorithm has obvious advantages in detection rate over the previous algorithms. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal

arXiv

引用

arXiv 2022年

作者： Wang, Tao Zhang, Kaihao Chen, Xuanxi Luo, Wenhan Deng, Jiankang Lu, Tong Cao, Xiaochun Liu, Wei Li, Hongdong Zafeiriou, Stefanos State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China College of Engineering and Computer Science Australian National University CanberraACT Australia Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China Department of Computing Imperial College London London United Kingdom Tencent Shenzhen518107 China

Face Restoration (FR) aims to restore High-Quality (HQ) faces from Low-Quality (LQ) input images, which is a domain-specific image restoration problem in the low-level computer vision area. The early face restoration methods mainly use statistic priors and degradation models, which are difficult to meet the requirements of real-world applications in practice. In recent years, face restoration has witnessed great progress after stepping into the deep learning era. However, there are few works to study deep learning-based face restoration methods systematically. Thus, this paper comprehensively surveys recent advances in deep learning techniques for face restoration. Specifically, we first summarize different problem formulations and analyze the characteristic of the face image. Second, we discuss the challenges of face restoration. Concerning these challenges, we present a comprehensive review of existing FR methods, including prior based methods and deep learning-based methods. Then, we explore developed techniques in the task of FR covering network architectures, loss functions, and benchmark datasets. We also conduct a systematic benchmark evaluation on representative methods. Finally, we discuss future directions, including network designs, metrics, benchmark datasets, applications, etc. We also provide an open-source repository for all the discussed methods, which is available at https://***/TaoWangzj/Awesome-Face-Restoration. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Local Gradient Difference Features for Classification of 2D-3D Natural Scene Text Images

Local Gradient Difference Features for Classification of 2D-...

引用

International Conference on Pattern Recognition

作者： Lokesh Nandanwar Palaiahnakote Shivakumara Ramachandra Raghavendra Tong Lu Umapada Pal Daniel Lopresti Nor Badrul Anuar Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Faculty of Information Technology and Electrical Engineering IIK NTNU Norway National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Computer Science & Engineering Lehigh University Bethlehem PA USA

Methods developed for normal 2D text detection do not work well for text that is rendered using decorative, 3D effects, etc. This paper proposes a new method for classification of 2D and 3D natural scene text images so that an appropriate recognition method can be chosen accordingly based on the classification results for better performance. The proposed method explores local gradient differences for obtaining candidate pixels, which represent a stroke. To study the spatial distribution of candidate pixels, we propose a measure, called COLD, which is denser for pixels toward the center of strokes and scattered for non-stroke pixels. This observation leads us to introduce mass features for extracting the regular spatial pattern of COLD, which indicates a 2D text image. The extracted features are fed into a Neural Network (NN) for classification. The proposed method is tested on (i) a new dataset introduced in this work (ii) a second dataset assembled from standard natural scene datasets (iii) Non-Text Image datasets which does not contain text, rather it contains objects. Experimental results of the proposed method on images with text and non-text show that the proposed method is independent of text. The proposed approach improves text detection and recognition performance significantly after classification.

关键词： Three-dimensional displays Image recognition Graphical models Text recognition Artificial neural networks Feature extraction Standards

来源：评论

学校读者我要写书评

暂无评论

A Service-Enhanced Task Offloading Method in MEC-Enabled IoV Networks

A Service-Enhanced Task Offloading Method in MEC-Enabled IoV...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Bohai Zhao Kai Peng Victor C.M. Leung Yunni Xia College of Engineering Huaqiao University Quanzhou P.R.China State Key Lab. for Novel Software Technology Nanjing University Nanjing P.R.China School of Computer Science and Software Engineering Shenzhen University Shenzhen P.R.China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada School of computers Chongqing University Chongqing P.R.China

To facilitate the evolution from independent transportation means to vehicle-to-infrastructure communications, traditional vehicle-to-vehicle (V2V) technologies are growing to a more advanced and generalized paradigm, i.e., the Internet of Vehicles (IoV). This paradigm has stimulated ever-increasing calling for more capabilities and intelligence for vehicles to foster the potential of supporting a plethora of emerging applications and ubiquitous automotive network access. Combining caching-aided communication and edge computing has been expected to be an advantageous framework to cope with the surging requirements for timely data processing and storage from intelligent IoV applications. In light of the delay restriction and the heterogeneity of edge service nodes (ESNs), we study the service-enhanced problem in edge-enabled IoV networks by configuring proactive service caching. Specifically, based on task scale and relational restrictions, we design an adaptive non-linear caching probability mapping function and further propose a proactive service-enhanced task offloading method in edge-enabled IoV networks named SEOEV. Performance evaluation demonstrates that SEOEV efficiently reduces task processing overhead in comparison to other comparative computing migration approaches.

关键词：

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：