检索结果-内蒙古大学图书馆

Part-Whole Relational Few-Shot 3D Point Cloud Semantic Segmentation

computers, Materials & Continua 2024年第3期78卷 3021-3039页

作者： Shoukun Xu Lujun Zhang Guangqi Jiang Yining Hua Yi Liu School of Computer Science and Artificial Intelligence Aliyun School of Big Data and School of SoftwareChangzhou UniversityChangzhou213164China Department of Computer Science University of AberdeenKing’s CollegeAberdeenAB243FXUK

This paper focuses on the task of few-shot 3D point cloud semantic *** some progress,this task still encounters many issues due to the insufficient samples given,e.g.,incomplete object segmentation and inaccurate semantic *** tackle these issues,we first leverage part-whole relationships into the task of 3D point cloud semantic segmentation to capture semantic integrity,which is empowered by the dynamic capsule routing with the module of 3D Capsule Networks(CapsNets)in the embedding ***,the dynamic routing amalgamates geometric information of the 3D point cloud data to construct higher-level feature representations,which capture the relationships between object parts and their ***,we designed a multi-prototype enhancement module to enhance the prototype ***,the single-prototype enhancement mechanism is expanded to the multi-prototype enhancement version for capturing rich ***,the shot-correlation within the category is calculated via the interaction of different samples to enhance the intra-category *** studies prove that the involved part-whole relations and proposed multi-prototype enhancement module help to achieve complete object segmentation and improve semantic ***,under the integration of these two modules,quantitative and qualitative experiments on two public benchmarks,including S3DIS and ScanNet,indicate the superior performance of the proposed framework on the task of 3D point cloud semantic segmentation,compared to some state-of-the-art methods.

关键词： Few-shot point cloud semantic segmentation CapsNets

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Scale Object Detection Algorithm for Foggy Traffic Scenarios

引用

computers, Materials & Continua 2025年第2期82卷 2451-2474页

作者： Honglin Wang Zitong Shi Cheng Zhu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Electrical&Computer Engineering University of Illinois at Urbana ChampaignUrbanaIL 61801USA

In foggy traffic scenarios, existing object detection algorithms face challenges such as low detection accuracy, poor robustness, occlusion, missed detections, and false detections. To address this issue, a multi-scale object detection algorithm based on an improved YOLOv8 has been proposed. Firstly, a lightweight attention mechanism, Triplet Attention, is introduced to enhance the algorithm’s ability to extract multi-dimensional and multi-scale features, thereby improving the receptive capability of the feature maps. Secondly, the Diverse Branch Block (DBB) is integrated into the CSP Bottleneck with two Convolutions (C2F) module to strengthen the fusion of semantic information across different layers. Thirdly, a new decoupled detection head is proposed by redesigning the original network head based on the Diverse Branch Block module to improve detection accuracy and reduce missed and false detections. Finally, the Minimum Point Distance based Intersection-over-Union (MPDIoU) is used to replace the original YOLOv8 Complete Intersection-over-Union (CIoU) to accelerate the network’s training convergence. Comparative experiments and dehazing pre-processing tests were conducted on the RTTS and VOC-Fog datasets. Compared to the baseline YOLOv8 model, the improved algorithm achieved mean Average Precision (mAP) improvements of 4.6% and 3.8%, respectively. After defogging pre-processing, the mAP increased by 5.3% and 4.4%, respectively. The experimental results demonstrate that the improved algorithm exhibits high practicality and effectiveness in foggy traffic scenarios.

关键词： Deep learning object detection foggy scenes traffic detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Approach for Targeted Knowledge Transfer in Self-Knowledge Distillation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2270-2283页

作者： Zimo Yin Jian Pu Yijie Zhou Xiangyang Xue the School of Computer Science Fudan University the Institute of Science and Technology for Brain Inspired Intelligence Fudan University IEEE

Knowledge distillation(KD) enhances student network generalization by transferring dark knowledge from a complex teacher network. To optimize computational expenditure and memory utilization, self-knowledge distillation(SKD) extracts dark knowledge from the model itself rather than an external teacher network. However, previous SKD methods performed distillation indiscriminately on full datasets, overlooking the analysis of representative samples. In this work, we present a novel two-stage approach to providing targeted knowledge on specific samples, named two-stage approach self-knowledge distillation(TOAST). We first soften the hard targets using class medoids generated based on logit vectors per class. Then, we iteratively distill the under-trained data with past predictions of half the batch size. The two-stage knowledge is linearly combined, efficiently enhancing model performance. Extensive experiments conducted on five backbone architectures show our method is model-agnostic and achieves the best generalization ***, TOAST is strongly compatible with existing augmentation-based regularization methods. Our method also obtains a speedup of up to 2.95x compared with a recent state-of-the-art method.

关键词： Cluster-based regularization iterative prediction refinement model-agnostic framework self-knowledge distillation(SKD) two-stage knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain TSK Fuzzy System Based on Semi-Supervised Learning for Epilepsy Classification

引用

computer Modeling in Engineering & sciences 2023年第11期137卷 1613-1633页

作者： Zaihe Cheng Yuwen Tao Xiaoqing Gu Yizhang Jiang Pengjiang Qian School of Internet of Things Wuxi Institute of TechnologyWuxi214121China School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China School of Computer Science and Artificial Intelligence Changzhou UniversityChangzhou213164China

Through semi-supervised learning and knowledge inheritance,a novel Takagi-Sugeno-Kang(TSK)fuzzy system framework is proposed for epilepsy data classification in this *** new method is based on the maximum mean discrepancy(MMD)method and TSK fuzzy system,as a basic model for the classification of epilepsy ***,formedical data,the interpretability of TSK fuzzy systems can ensure that the prediction results are traceable and ***,in view of the deviation in the data distribution between the real source domain and the target domain,MMD is used to measure the distance between different data *** objective function is constructed according to the MMD distance,and the distribution distance of different datasets is minimized to find the similar characteristics of different *** introduce semi-supervised learning to further explore the relationship between *** on the MMD method,a semi-supervised learning(SSL)-MMD method is constructed by using pseudo-tags to realize the data distribution alignment of the same *** addition,the idea of knowledge dissemination is used to learn pseudo-tags as additional data ***,for epilepsy classification,the cross-domain TSK fuzzy system uses the cross-entropy function as the objective function and adopts the back-propagation strategy to optimize the *** experimental results show that the new method can process complex epilepsy data and identify whether patients have epilepsy.

关键词： Takagi-Sugeno-Kang fuzzy systems back propagation semi-supervised learning inheritancemechanism transfer learning

来源：评论

学校读者我要写书评

暂无评论

Characterizing the app recommendation relationships in the iOS app store: a complex network's perspective

引用

science China(Information sciences) 2025年第4期68卷 284-299页

作者： Gang HUANG Fuqi LIN Yun MA Haoyu WANG Qingxiang WANG Gareth TYSON Xuanzhe LIU Key Lab of High Confidence Software Technologies (Peking University) Ministry of Education School of Computer Science Peking University Institute for Artificial Intelligence Peking University School of Cyber Science and Engineering Huazhong University of Science and Technology Alibaba Group Hong Kong University of Science and Technology (Guangzhou)

Mobile apps have become widely adopted in our daily lives. To facilitate app discovery, most app markets provide recommendations for users, which may significantly impact how apps are accessed. However, little has been known about the underlying relationships and how they reflect(or affect) user behaviors. To fill this gap, we characterize the app recommendation relationships in the i OS app store from the perspective of the complex network. We collect a dataset containing over 1.3 million apps and 50 million app recommendations. This dataset enables us to construct a complex network that captures app recommendation relationships. Through this, we explore the recommendation relationships between mobile apps and how these relationships reflect or affect user behavior patterns. The insights gained from our research can be valuable for understanding typical user behaviors and identifying potential policy-violating apps.

关键词： mobile app recommendation complex network user behavior policy-violating app

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Trainer-Based Deep Q-Network for Dynamic Flexible Job Shop Scheduling

引用

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Liu, Yun Zhang, Fangfang Sun, Yanan Zhang, Mengjie College of Computer Science Sichuan University Chengdu PR China Center for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

Dynamic flexible job shop scheduling (DFJSS) aims to achieve the optimal efficiency for production planning in the face of dynamic events. In practice, deep Q-network (DQN) algorithms have been intensively studied for solving various DFJSS problems. However, these algorithms often cause moving targets for the given job-shop state. This will inevitably lead to unstable training and severe deterioration of the performance. In this paper, we propose a training algorithm based on genetic algorithm to efficiently and effectively address this critical issue. Specifically, a state feature extraction method is first developed, which can effectively represent different job shop scenarios. Furthermore, a genetic encoding strategy is designed, which can reduce the encoding length to enhance search ability. In addition, an evaluation strategy is proposed to calculate a fixed target for each job-shop state, which can avoid the parameter update of target networks. With the designs, the DQNs could be stably trained, thus their performance is greatly improved. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art peer competitors in terms of both effectiveness and generalizability to multiple scheduling scenarios with different scales. In addition, the ablation study also reveals that the proposed algorithm can outperform the DQN algorithms with different updating frequencies of target networks. IEEE

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Novel Rifle Number Recognition Based on Improved YOLO in Military Environment

引用

computers, Materials & Continua 2024年第1期78卷 249-263页

作者： Hyun Kwon Sanghyun Lee Department of Artificial Intelligence and Data Science Korea Military AcademySeoulKorea Graduate School of Information Security Korea Advanced Institute of Science and TechnologyDaejeonKorea

Deep neural networks perform well in image recognition,object recognition,pattern analysis,and speech *** military applications,deep neural networks can detect equipment and recognize *** military equipment,it is necessary to detect and recognize rifle management,which is an important piece of equipment,using deep neural *** have been no previous studies on the detection of real rifle numbers using real rifle image *** this study,we propose a method for detecting and recognizing rifle numbers when rifle image data are *** proposed method was designed to improve the recognition rate of a specific dataset using data fusion and transfer *** the proposed method,real rifle images and existing digit images are fusedas trainingdata,andthe final layer is transferredto theYolov5 *** detectionand recognition performance of rifle numbers was improved and analyzed using rifle image and numerical *** used actual rifle image data(K-2 rifle)and numeric image datasets,as an experimental *** was used as the machine learning *** results show that the proposed method maintains 84.42% accuracy,73.54% precision,81.81% recall,and 77.46% F1-score in detecting and recognizing rifle *** proposed method is effective in detecting rifle numbers.

关键词： Machine learning deep neural network rifle number recognition detection

来源：评论

学校读者我要写书评

暂无评论

Explaining the better generalization of label distribution learning for classification

引用

science China(Information sciences) 2025年第5期68卷 348-361页

作者： Jing WANG Xin GENG School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(Southeast University) Ministry of Education

Label distribution learning(LDL) has shown advantages over traditional single-label learning(SLL) in many realworld applications, but its superiority has not been theoretically understood. In this paper, we attempt to explain why LDL generalizes better than SLL. Label distribution has rich supervision information such that an LDL method can still choose the sub-optimal label from label distribution even if it neglects the optimal one. In comparison, an SLL method has no information to choose from when it fails to predict the optimal label. The better generalization of LDL can be credited to the rich information of label distribution. We further establish the label distribution margin theory to prove this explanation; inspired by the theory,we put forward a novel LDL approach called LDL-LDML. In the experiments, the LDL baselines outperform the SLL ones, and LDL-LDML achieves competitive performance against existing LDL methods, which support our explanation and theories in this paper.

关键词： label distribution learning classification generalization label distribution margin label ambiguity neural network

来源：评论

学校读者我要写书评

暂无评论

SAR Ship Detection Based on Multi-Scale Feature Cross Fusion

引用

Progress in Electromagnetics Research B 2025年 110卷 149-161页

作者： Ren, Xiaozhen Zhou, Peiyuan Liu, Gang School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China School of Information Science and Engineering Henan University of Technology Zhengzhou450001 China

Synthetic aperture radar (SAR) ship detection plays a significant role in ocean monitoring. However, the current SAR ship detection methods face limitations in detecting small and dense ships. To address these issues, a novel SAR ship detection method based on multi-scale feature cross-fusion (MFCNet) is proposed in this paper. In the proposed model, a feature extraction network with a spatial fusion attention mechanism (FESNet) is designed to improve the capability of the backbone network in feature extraction. A multiintersection spatial pyramid pooling (MISPP) module is proposed to expand the receptive field and enhance the semantic information. Furthermore, a feature cross-fusion network (FCFNet) is designed to comprehensively integrate features of different scales for enhancing SAR ship detection performance. Experimental results demonstrate that the proposed model achieves high detection performance on the SSDD and HRSID datasets, providing more reliable technical support for ship detection in maritime environments. © (2025), (Electromagnetics Academy). All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Novel Predictive Model for Edge Computing Resource Scheduling Based on Deep Neural Network

引用

computer Modeling in Engineering & sciences 2024年第4期139卷 259-277页

作者： Ming Gao Weiwei Cai Yizhang Jiang Wenjun Hu Jian Yao Pengjiang Qian School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China The Center for Intelligent Systems and Applications Research School of Artificial Intelligence and Computer ScienceJiangnan UniversityWuxi214122China School of Information Engineering Huzhou UniversityHuzhou313000China

Currently,applications accessing remote computing resources through cloud data centers is the main mode of operation,but this mode of operation greatly increases communication latency and reduces overall quality of service(QoS)and quality of experience(QoE).Edge computing technology extends cloud service functionality to the edge of the mobile network,closer to the task execution end,and can effectivelymitigate the communication latency ***,the massive and heterogeneous nature of servers in edge computing systems brings new challenges to task scheduling and resource management,and the booming development of artificial neural networks provides us withmore powerfulmethods to alleviate this ***,in this paper,we proposed a time series forecasting model incorporating Conv1D,LSTM and GRU for edge computing device resource scheduling,trained and tested the forecasting model using a small self-built dataset,and achieved competitive experimental results.

关键词： Edge computing resource scheduling predictive models

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：