检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Mei Yu Pengtao Fan Mankun Zhao Wenbin Zhang Yue Zhao Ming Yang Jian Yu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Advanced Networking(TANK Lab) Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China College of Computing and Software Engineering Kennesaw State University Marietta GA USA

In the real world, the Knowledge Graph(KG) is dynamic and new entities are added at any time. Therefore, open-world Knowledge Graph Completion(KGC) was proposed to approach new-added entities, but previous approaches often introduced too much noise when introducing external text resources for new entities. To alleviate this problem, knowledge graph zero-shot relational learning (KGZSL) has recently attracted more attention. Generative Adversarial Networks (GANs) are frequently used in KGZSL to connect existing relation descriptions to the domain of knowledge graphs. However, these methods ignore the impact of existing entities on embeddings for unidentified relational representations and in-stead concentrate on examining the connection between relational textual texts and knowledge network structures. In this work, we propose a multi-block attention framework using relation Description Generative Adversarial Networks (desGAN) jointing KG and text representation and address model collapse and training stability problems in previous studies. The core idea of our method is to obtain the background knowledge graph information and the relation representation through and multi-block attention layer and the desGAN, then a connection between the structured KG semantic space and the unstructured text semantic space of the new entity is established, forcing the entity pair to be closer to their real relation. Experimental results on the knowledge graph zeroshot relational learning dataset demonstrate that our MASZSL has a faster convergence speed and achieves state-of-the-art performance on this task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combination of Translation and Rotation in Dual Quaternion Space for Temporal Knowledge Graph Completion

Combination of Translation and Rotation in Dual Quaternion S...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ruiguo Yu Tao Liu Jian Yu Wenbin Zhang Yue Zhao Ming Yang Mankun Zhao Jiujiang Guo College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Advanced Networking(TANK Lab) Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China College of Computing and Software Engineering Kennesaw State University Marietta GA USA

Compared with static knowledge graphs (KGs) temporal KGs record the dynamic relations between entities over time, therefore, research on temporal Knowledge Graph Completion (KGC) attracts much attention. Temporal KGs exhibit complex temporal relation patterns, such as multiple relations. However, existing methods can hardly model all the relation patterns and apply to the temporal KGs. In this paper, we propose a novel temporal KGC method that Combining Translation and Rotation (ComTR) in Dual Quaternion Space for temporal KGC. Specifically, we use dual-quaternion-based multiplication to model timestamps and relations as the combination of translation and rotation operations. We analyze the relation patterns of temporal KGs in detail and demonstrate that our method can model all the relation patterns in temporal KGs. Empirically, we show that ComTR can achieve the state-of-the-art performances over four temporal KGC benchmarks datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interaction-Aware Cut-In Trajectory Prediction and Risk Assessment in Mixed Traffic

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1752-1762页

作者： Xianglei Zhu Wen Hu Zejian Deng Jinwei Zhang Fengqing Hu Rui Zhou Keqiu Li Fei-Yue Wang the College of Intelligence and Computing Tianjin UniversityTianjin 300350 the China Automotive Technology and Research Center Co.Ltd. Tianjin 300300China the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body College of Mechanical and Vehicle EngineeringHunan UniversityChangsha 410082China the Department of Mechanical and Mechatronics Engineering University of WaterlooWaterlooON N2L3G1Canada the School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China the Macao University of Science and Technology MacaoChina the Waytous Inc. Qingdao 266000China IEEE the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Accurately predicting the trajectories of surrounding vehicles and assessing the collision risks are essential to avoid side and rear-end collisions caused by *** improve the safety of autonomous vehicles in the mixed traffic,this study proposes a cut-in prediction and risk assessment method with considering the interactions of multiple traffic *** integration of the support vector machine and Gaussian mixture model(SVM-GMM)is developed to simultaneously predict cut-in behavior and *** dimension of the input features is reduced through Chebyshev fitting to improve the training efficiency as well as the online inference *** on the predicted trajectory of the cut-in vehicle and the responsive actions of the autonomous vehicles,two risk measurements are introduced to formulate the comprehensive interaction risk through the combination of Sigmoid function and Softmax ***,the comparative analysis is performed to validate the proposed method using the naturalistic driving *** results show that the proposed method can predict the trajectory with higher precision and effectively evaluate the risk level of a cut-in maneuver compared to the methods without considering interaction.

关键词： Cut-in behavior interaction-aware mixed traffic risk assessment trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

Survey on Foundation Models for Prognostics and Health Management in Industrial Cyber-Physical Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2024年 2卷 264-280页

作者： Liu, Ruonan Zhang, Quanhu Han, Te Yang, Boyuan Zhang, Weidong Yin, Shen Zhou, Donghua Shanghai Jiao Tong University Department of Automation Shanghai200240 China Tianjin University College of Intelligence and Computing Tianjin300350 China Beijing Institute of Technology Center for Energy and Environmental Policy Research Beijing100081 China Beijing Institute of Technology School of Management Beijing100081 China Beijing Laboratory for System Engineering of Carbon Neutrality Beijing100081 China Nanjing University Center for Advanced Control and Smart Operations Suzhou215163 China Hainan University School of Information and Communication Engineering Haikou570228 China Shanghai Jiaotong University Department of Automation Shanghai200240 China Norwegian University of Science and Technology Trondheim7491 Norway

Industrial Cyber-Physical Systems (ICPS) integrating disciplines such as computer science, communication technology, and engineering, have become a crucial component of modern manufacturing and industry. However, ICPS faces numerous challenges during long-term operation, including equipment faults, performance degradation, and security threats, etc. To achieve efficient maintenance and management, prognostics and health management (PHM) has been widely applied in the critical tasks of ICPS such as fault prediction, health monitoring, and maintenance decision-making. The emergence of large-scale foundation models (LFMs) like BERT and GPT marks a significant advancement in artificial intelligence (AI) technology, demonstrating substantial application potential in multiple fields. The accumulation of AI technology, rapid development of LFMs, and the abundance of industrial data and industrial process knowledge provide the foundational conditions for the construction and advancement of industrial LFMs. However, there is currently a lack of consensus on applying LFMs of PHM in ICPS, necessitating a systematic review and roadmap to clarify future development directions. To bridge this gap, this survey provides a comprehensive survey and understanding of the recent advances in LFMs of PHM in ICPS. It provides valuable references for decision makers and researchers in the industry, and helps to further improve the reliability, availability and safety of ICPS. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection

arXiv

引用

arXiv 2023年

作者： Chen, Zixuan Xie, Xiaohua Yang, Lingxiao Lai, Jian-Huang School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou510006 China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Anomaly detectors are widely used in industrial manufacturing to detect and localize unknown defects in query images. These detectors are trained on anomaly-free samples and have successfully distinguished anomalies from most normal samples. However, hard-normal examples are scattered and far apart from most normal samples, and thus they are often mistaken for anomalies by existing methods. To address this issue, we propose Hard-normal Example-aware Template Mutual Matching (HETMM), an efficient framework to build a robust prototype-based decision boundary. Specifically, HETMM employs the proposed Affine-invariant Template Mutual Matching (ATMM) to mitigate the affection brought by the affine transformations and easy-normal examples. By mutually matching the pixel-level prototypes within the patch-level search spaces between query and template set, ATMM can accurately distinguish between hard-normal examples and anomalies, achieving low false-positive and missed-detection rates. In addition, we also propose PTS to compress the original template set for speed-up. PTS selects cluster centres and hard-normal examples to preserve the original decision boundary, allowing this tiny set to achieve comparable performance to the original one. Extensive experiments demonstrate that HETMM outperforms state-of-the-art methods, while using a 60-sheet tiny set can achieve competitive performance and real-time inference speed (around 26.1 FPS) on a Quadro 8000 RTX GPU. HETMM is training-free and can be hot-updated by directly inserting novel samples into the template set, which can promptly address some incremental learning issues in industrial manufacturing. Copyright © 2023, The Authors. All rights reserved.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

arXiv

引用

arXiv 2023年

作者： Wu, Xiao-Ming Zheng, Dian Liu, Zuhao Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

arXiv

引用

arXiv 2023年

作者： Fu, Shenghao Yan, Junkai Gao, Yipeng Xie, Xiaohua Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy tradeoff. The code is available at https://***/iSEE-laboratory/ASAG. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Deep Models on Salient Object Detection

SSRN

引用

SSRN 2023年

作者： Zhou, Huajun Lin, Yang Yang, Lingxiao Lai, Jianhuang Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

Deep network-based methods have continuously refreshed state-of-the-art performance on the Salient Object Detection (SOD) task. However, the performance discrepancy caused by different implementation details may conceal the real progress. In this paper, we construct a SALient Object Detection (SALOD) benchmark to ensure a fair and comprehensive evaluation by unifying the implementation settings of SOD methods. We aim to reveal the reasons behind recent progress by conducting a comprehensive examination of the impact of the network structure, training strategy, and loss function on accuracy. Based on the experimental results, first, we find that U-shaped networks, both older and more recent, still achieve better performance than other recently proposed structures. Second, the ablation study on training strategy proves its significant impact on SOD performance. Third, we provide a comprehensive analysis on existing loss functions and propose a new Edge-Aware (EA) loss function in response. At last, an objectness shifting experiment stands on a new perspective to validate the generalizability of SOD methods. Code is available at https://***/moothes/SALOD. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via...

引用

International Conference on Computer Vision (ICCV)

作者： Shenghao Fu Junkai Yan Yipeng Gao Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy trade-off. The code is available at https://***/iSEE-laboratory/ASAG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Lu, Yanzuo Shen, Meng Ma, Andy J. Xie, Xiaohua Lai, Jian-Huang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangzhou China

Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer. Existing UniDA methods may suffer from the problems of overlooking intra-domain variations in the target domain and difficulty in separating between the similar known and unknown class. To address these issues, we propose a novel Mutual Learning Network (MLNet) with neighborhood invariance for UniDA. In our method, confidence-guided invariant feature learning with self-adaptive neighbor selection is designed to reduce the intra-domain variations for more generalizable feature representation. By using the cross-domain mixup scheme for better unknown-class identification, the proposed method compensates for the misidentified known-class errors by mutual learning between the closed-set and open-set classifiers. Extensive experiments on three publicly available benchmarks demonstrate that our method achieves the best results compared to the state-of-the-arts in most cases and significantly outperforms the baseline across all the four settings in UniDA. Code is available at https://***/YanzuoLu/MLNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge management

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：