检索结果-内蒙古大学图书馆

MMLN: Multi-directional and Multi-constraint Learning Network for Remote Sensing Imagery Semantic Segmentation

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2024年 1-16页

作者： Sun, Hang Xie, Yongchang Ren, Dong Wen, Fangqing Tong, Lyuyang Chang, Laibin Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang China Institute of Vehicle Information Control and Network Technology Hubei University of Automotive Technology Shiyan China School of Computer Science Wuhan University Wuhan China

Recent advances in satellite remote sensing technology and computer technology have significantly impacted practical applications in remote sensing image segmentation. However, the prevalent hybrid segmentation models that combine Convolutional Neural Networks (CNNs) and Transformers, often overlook the critical exploration of local and global feature correlations across various scales. This exploration is essential for learning more representative features and strengthening context modeling capabilities. Additionally, the decoding layers of these models do not effectively exploit the pixel-level semantic relationships within cross-layer feature maps, thereby limiting the models' ability to discern small object features. To address these challenges, this paper introduces a Multi-directional and Multi-constraint Learning Network (MMLN) designed for semantic segmentation of remote sensing imagery. This network features a Multi-directional Dynamic Complement Decoder (MDCD), which enhances the interaction between local and global features in the feature space, and subsequently improves the feature discrimination within the segmentation network. Moreover, a Multi-constraint Saliency Boundary-adaptive Module (MSBM) is implemented to reinforce the spatial constraints on saliency at the edge regions and ensure semantic consistency along the mask boundaries. This, in turn, augments the segmentation model's capability to detect small objects. The evaluation on four datasets reveals that the MMLN outperforms the existing state-of-the-art methods in remote sensing imagery segmentation. The code is available at https://***/zhongyas/MMLN. Authors

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Embedding Method Based on Entity Metric Learning 23

Knowledge Graph Embedding Method Based on Entity Metric Lear...

引用

9th International Conference on computing and Artificial Intelligence, ICCAI 2023

作者： He, Meng Duan, Lijuan Zhang, Baochang Han, Shengwen Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Trusted Computing National Engineering Laboratory for Key Technologies of Information Security Level Protection China Institute of Artificial Intelligence Beihang University China Faculty of Information Technology Beijing University of Technology China

ISBN: (纸本)9781450399029

A knowledge graph is a knowledge base of graph structure that stores massive facts and their relations in the form of triplets. Embedding entities and relations in knowledge graph into low-dimensional continuous vector space is of great significance for downstream tasks, whereas most existing methods give an end-to-end fixed representation. Based on deep metric learning, we give different embeddings for the same entity in different relations and positions, thus dynamically representing entities in knowledge graph and effectively modeling complex relations. In addition, a path-based negative sampling method is proposed to widen the distance between similar entities to better deal with the aggregation problem of embedding entities in the representation space under one-to-many relation. Experiments show that the MRR and Hit@1 of this method on the linked prediction dataset FB15k-237 reach 0.360 and 0.267 respectively, which are higher than the mainstream distance models and semantic matching models. Finally, the MRR-Dimension curves demonstrates that our model can perform well in both low and high embedding dimensions and has the potential to be applied to large-scale knowledge graph. © 2023 Copyright held by the owner/author(s).

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

An Algebraic Multigrid-Based Physical Factorization Preconditioner for the Multi-Group Radiation Diffusion Equations in Three Dimensions

引用

Numerical Mathematics(Theory,Methods and Applications) 2023年第2期16卷 410-432页

作者： Xiaoqiang Yue Zekai Zhang Xiaowen Xu Shuying Zhai Shi Shu National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing&Information Processing of Ministry of EducationHunan Key Laboratory for Computation and Simulation in Science and EngineeringXiangtan UniversityXiangtan 411105China Laboratory of Computational Physics Institute of Applied Physics and Computational MathematicsBeijing 100094China School of Mathematical Sciences Huaqiao UniversityQuanzhou 362021China.

The paper investigates the robustness and parallel scaling properties of a novel physical factorization preconditioner with algebraic multigrid subsolves in the iterative solution of a cell-centered finite volume discretization of the threedimensional multi-group radiation diffusion *** key idea is to take advantage of a particular kind of block factorization of the resulting system matrix and approximate the left-hand block matrix selectively spurred by parallel processing *** spectral property of the preconditioned matrix is then *** practical strategy is considered sequentially and in ***,numerical results illustrate the numerical robustness,computational efficiency and parallel strong and weak scalabilities over the real-world structured and unstructured coupled problems,showing its competitiveness with many existing block preconditioners.

关键词： Radiation diffusion equations physical factorization preconditioning algebraic multigrid parallel and distributed computing

来源：评论

学校读者我要写书评

暂无评论

HWD-YOLO:A New Vision-Based Helmet Wearing Detection Method

引用

Computers, Materials & Continua 2024年第9期80卷 4543-4560页

作者： Licheng Sun Heping Li Liang Wang College of Information Science and Technology Beijing University of TechnologyBeijing100124China Chinese Institute of Coal Science Beijing100013China State Key Laboratory for Intelligent Coal Mining and Strata Control Beijing100013China Engineering Research Center of Digital Community of Ministry of Education Beijing100124China

It is crucial to ensure workers wear safety helmets when working at a workplace with a high risk of safety accidents,such as construction sites and mine *** existing methods can achieve helmet detection in images,their accuracy and speed still need improvements since complex,cluttered,and large-scale scenes of real workplaces cause server occlusion,illumination change,scale variation,and perspective ***,a new safety helmet-wearing detection method based on deep learning is ***,a new multi-scale contextual aggregation module is proposed to aggregate multi-scale feature information globally and highlight the details of concerned objects in the backbone part of the deep neural ***,a new detection block combining the dilate convolution and attention mechanism is proposed and introduced into the prediction *** block can effectively extract deep featureswhile retaining information on fine-grained details,such as edges and small ***,some newly emerged modules are incorporated into the proposed network to improve safety helmetwearing detection performance *** experiments on open dataset validate the proposed *** reaches better performance on helmet-wearing detection and even outperforms the state-of-the-art *** be more specific,the mAP increases by 3.4%,and the speed increases from17 to 33 fps in comparison with the baseline,You Only Look Once(YOLO)version 5X,and themean average precision increases by 1.0%and the speed increases by 7 fps in comparison with the YOLO version *** generalization ability and portability experiment results show that the proposed improvements could serve as a springboard for deep neural network design to improve object detection performance in complex scenarios.

关键词： Object detection deep learning safety helmet wearing detection feature extraction attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Optimized Service Function Deployment in Edge computing Networks Using Deep Reinforcement Learning 7

Optimized Service Function Deployment in Edge Computing Netw...

引用

7th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2024

作者： Huo, Liuwei Zhu, Bowen Zhao, Dongcheng Institute of intelligent computing University of Electronic Science and Technology of China Chengdu China School of Communication and Information Engineering University of Electronic Science and Technology of China Chengdu China Tianfu Jiangxi Laboratory Chengdu China

ISBN: (纸本)9798331529314

The deployment of service function chains (SFCs) in integrated edge computing networks presents significant challenges, including optimizing resource utilization, minimizing latency, and reducing energy consumption. These challenges arise from the dynamic nature of workloads, varying network conditions, and complex service function dependencies. Conventional optimization approaches often struggle to handle these complexities, as they depend on static models and assumptions that may not apply in practical situations. This paper introduces an innovative solution using deep reinforcement learning (DRL) to overcome these limitations. By modeling the deployment problem as a Markov decision process, we utilize the DRL's capability to learn optimal policies through iterative trial and error interactions with the environment. Our method adaptively adjusts service function placement in real time, accounting for workload variability, service dependencies, and network conditions. Comprehensive simulations demonstrate that our proposed approach achieves significant improvements in terms of latency reduction, resource utilization, and energy consumption compared to conventional methods, and can provide a new solution for SFC deployment. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer 29

Improving Fake News Detection of Influential Domain via Doma...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Nan, Qiong Wang, Danding Zhu, Yongchun Sheng, Qiang Shi, Yuhui Cao, Juan Li, Jintao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Both real and fake news in various domains, such as politics, health, and entertainment are spread via online social media every day, necessitating fake news detection for multiple domains. Among them, fake news in specific domains like politics and health has more serious potential negative impacts on the real world (e.g., the infodemic led by COVID-19 misinformation). Previous studies focus on multi-domain fake news detection, by equally mining and modeling the correlation between domains. However, these multi-domain methods suffer from a seesaw problem: the performance of some domains is often improved at the cost of hurting the performance of other domains, which could lead to an unsatisfying performance in specific domains. To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains. To transfer coarse-grained domain-level knowledge, we train a general model with data of all domains from the meta-learning perspective. To transfer fine-grained instance-level knowledge and adapt the general model to a target domain, we train a language model on the target domain to evaluate the transferability of each data instance in source domains and re-weigh each instance’s contribution. Offline experiments on two datasets demonstrate the effectiveness of DITFEND. Online experiments show that DITFEND brings additional improvements over the base models in a real-world scenario. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Task Allocation for Heterogeneous Multi-Robot System under Communication Constraints 6

Dynamic Task Allocation for Heterogeneous Multi-Robot System...

引用

6th IEEE information technology, Networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Li, Jun Cai, Zhongxuan Li, Minglong Huang, Wanrong Zhang, Yongjun National University of Defense Technology Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer China

ISBN: (纸本)9781665460033

Multi-robot system has important application potential in disaster rescue and other dangerous scenarios, in which task allocation is the basis for multi-robot cooperation to complete tasks. Due to the limited ability of individual robots, many complex scenarios requires coordination of different types of robot, e.g. robots for search, communication, rescue and so on. At the same time, communication is often limited in a wide range of scenarios. This brings two challenges in the realistic environment: heterogeneous multi-robot cooperation problem and communication constraint problem. This paper proposes a task allocation method based on hierarchical auction and dynamic grouping. By introducing a dynamic grouping algorithm to the general allocation procedure, we simultaneously optimize the number of robots in each group and the communication distance between robots. Then the communication loss rate can be reduced to improve task execution efficiency. Simulations of a communication constrained search and rescue scenario are conducted to verify the proposed algorithm, which are compared with the vanilla auction algorithm and a hierarchical approach on static grouping. The results show that our method surpasses the baseline on both task achievement and communication performance. © 2023 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multi-Objective Neural Architecture Search for Generalized Cognitive Diagnosis Models 5

Evolutionary Multi-Objective Neural Architecture Search for ...

引用

5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023

作者： Yang, Shangshang Zhen, Cheng Tian, Ye Ma, Haiping Liu, Yuanchao Zhang, Panpan Zhang, Xingyi School of Artificial Intelligence Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China Automation for Process Industries Northeastern University State Key Laboratory of Synthetical Shenyang China

ISBN: (纸本)9798350393521

Cognitive diagnosis models (CDMs) with high generalization are essential for intelligent education systems to reveal students' knowledge states in multiple datasets. However, existing CDMs' architectures are designed dependent on researcher expertise and experience from observing and summarizing partial students' learning behaviors, which makes handcrafted models not cover all learning behaviors well and thus limits their generalization. To develop generalized CDMs, this paper proposes an evolutionary neural architecture search to design CDMs' architectures effective on multiple datasets automatically. Specifically, we first formulate the search task as a multi-objective optimization problem (MOP), which maximizes model performance on multiple datasets containing learning behaviors as many as possible to ensure model generalization. Then, an expressive search space is devised to contain as many potential architectures as possible, where each architecture is denoted by a unified form, taking three given inputs and integrating them in a linear or no-linear manner for prediction. Finally, an evolutionary algorithm with a tailored deduplication strategy is employed to solve the MOP, where each architecture is further represented by a single-root computation tree for easy optimization. Experiments on multiple datasets demonstrate the generalization and effectiveness of the best architecture searched by the proposed approach, and the searched architecture also holds as good interpretability as handcrafted architectures. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

REVISITING GRAPH ADVERSARIAL ATTACK AND DEFENSE FROM A DATA DISTRIBUTION PERSPECTIVE 11

REVISITING GRAPH ADVERSARIAL ATTACK AND DEFENSE FROM A DATA ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Li, Kuan Liu, Yang Ao, Xiang He, Qing Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China

Recent studies have shown that structural perturbations are significantly effective in degrading the accuracy of Graph Neural Networks (GNNs) in the semi-supervised node classification (SSNC) task. However, the reasons for the destructive nature of gradient-based methods have not been explored in-depth. In this work, we discover an interesting phenomenon: the adversarial edges are not uniformly distributed on the graph, and a majority of perturbations are generated around the training nodes in poisoning attacks. Combined with this phenomenon, we provide an explanation for the effectiveness of the gradient-based attack method from a data distribution perspective and revisit both poisoning attack and evasion attack in SSNC. From this new perspective, we empirically and theoretically discuss some other attack tendencies. Based on the analysis, we provide nine practical tips on both attack and defense and meanwhile leverage them to improve existing attack and defense methods. Moreover, we design a fast attack method and a self-training defense method, which outperform the state-of-the-art methods and can effectively scale to large graphs like ogbn-arxiv. We validate our claims through extensive experiments on four benchmark datasets. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Ingredient-Guided RGB-D Fusion Network for Nutritional Assessment

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 156-166页

作者： Feng, Zhihui Xiong, Hao Min, Weiqing Hou, Sujuan Duan, Huichuan Liu, Zhonghua Jiang, Shuqiang Shandong Normal University School of Information Science and Enginering Jinan250358 China Macquarie University Centre for Health Informatics Macquarie ParkNSW2109 Australia Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Zhejiang Ocean University School of Information Engineering Zhoushan316022 China

The nutritional value of agricultural products is an important indicator for evaluating their quality, which directly affects people's dietary choices and overall well-being. Nutritional assessment studies provide a scientific basis for the production, processing, and marketing of food by analyzing the nutrients they contain. Traditional methods often struggle with suboptimal accuracy and can be time consuming, as well as a shortage of professionals. The progress in artificial intelligence has revolutionized dietary health by offering more accessible methods for food nutritional assessment using vision-based approaches. However, existing vision-based methods using RGB images often face challenges due to varying lighting conditions, impacting the accuracy of nutritional assessment. An alternative is the RGB-D fusion method, which combines RGB images and depth maps. Yet, these methods typically rely on simple fusion techniques that do not ensure precise assessment. Additionally, current vision-based methods struggle to detect small components like oils and sugars on food surfaces, crucial for determining ingredient information and ensuring accurate nutritional assessment. In this pursuit, we propose a novel ingredient-guided RGB-D fusion network that integrates RGB images with depth maps and enables more reliable nutritional assessment guided by ingredient information. Specifically, the multifrequency bimodality fusion module is designed to leverage the correlation between the RGB image and the depth map within the frequency domain. Furthermore, the progressive-fusion module and ingredient-guided module leverage ingredient information to explore the potential correlation between ingredients and nutrients, thereby enhancing the guidance for nutritional assessment learning. We evaluate our approach on a variety of ablation settings on Nutrition5k, where it consistently outperforms state-of-the-art methods. © 2023 IEEE.

关键词： Medicinal chemistry

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：