检索结果-内蒙古大学图书馆

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Zhou, Yongjie Xiong, Jinbo Bi, Renwan Tian, Youliang State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Fujian Provincial Key Laboratory of Network System Information Security College of Computer and Cyberspace Security Fujian Normal University FJ Fuzhou350117 China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

The connected autonomous vehicles (CAVs) are a key component of intelligent transportation systems (ITS) where vehicles communicate with each other to exchange sensing data from on-board sensors (e.g., high-definition cameras and lidar). For the sake of the category and location privacy leakage of sensing images shared by CAVs and computational inefficiency of privacy-preserving object detection framework in edge computing environment, we propose a lightweight and privacy-preserving detection framework (PPDF) to support secure extraction, classification and detection of image features, and achieve the goal of data transmission and computing security under the collaborative detection process of edge nodes. Particularly, we design a secure clustering prediction protocol of object anchors, a secure object classification and regression protocol, secure object upsampling and secure feature fusion protocols. Finally, PPDF based on edge-cooperation was constructed and two non-collusive edge servers were used to perform PPDF. Theoretical analysis of correctness, security and complexity indicate that PPDF can not only realize correctness of object detection, but also let category and location privacy of images are protected effectively and have excellent accuracy. Actual performance evaluation shows that PPDF can achieve the same detection accuracy as original YOLOv3-SPP model. At the same time, compared with homomorphic encryption and multi-round iterative calculation schemes, PPDF has obvious advantages in terms of computational cost and communication overhead. © 2022 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Federated Hybrid-Supervised Learning for Universal Medical Image Segmentation

Federated Hybrid-Supervised Learning for Universal Medical I...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Shenhai Wen, Sian Li, Congyu Chen, Qing Li, Laquan College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China School of Science Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798350368741

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG. © 2025 IEEE.

关键词： federated learning hybrid-supervised learning medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

arXiv

引用

arXiv 2024年

作者： Chen, Ziyang Long, Wei Yao, He Zhang, Yongjun Wang, Bingshu Qin, Yongbin Wu, Jia College of Computer Science and Technology The State Key Laboratory of Public Big Data Institute of Artificial Intelligence Guizhou University China College of Software Northwest Polytechnical University China

Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Channel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at MoCha-Stereo. Copyright © 2024, The Authors. All rights reserved.

关键词： Stereocenters

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Three Multispectral Images in Classification with Different Methods 24

A Comparative Analysis of Three Multispectral Images in Clas...

引用

13th International Conference on Computing and Pattern Recognition, ICCPR 2024

作者： Chen, Feng Gao, Zhibin Song, Yuejun College of Computer and Information Engineering Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of Technology Xiamen China College of Computer and Information Engineering Xiamen University of Technology Xiamen China Jiangxi Key Laboratory of Watershed Soil and Water Conservation Jiangxi Academy of Water Science and Engineering Nanchang China

ISBN: (纸本)9798400717482

Benefited from the increased satellite observations with medium spatial resolution, land use/cover mapping at local to global scales has provided important supports for society and academy community. For specific purposes (e.g., disaster assessment, detecting surface abrupt change), it is needed to increase the observation frequency, through combining different satellite sensors (i.e. as virtual constellation). However, many factors challenge this combination in practice, in which the comparability issue in sensor settings should be considered among various payload platforms. In this study, from the perspective of practical application, a comparative analysis of land use/cover mapping was investigated, with focusing on three observations by the Gaofen-1 (GF-1) wide field of view (WFV), Sentinel-2A Multi-Spectral Instrument (MSI), and Landsat-8 Operational Land Imager (OLI) respectively. Four methods were implemented in classification experiments. Preliminary results showed that the Sentinal-2A MSI outperformed the GF-1 WFV and the Landsat-8 OLI in classification, no matter which classifier was considered. Meanwhile, the higher spatial resolution of the GF-1 WFV certainly compensated its lack of spectral channels compared against the Landsat-8 OLI. The choice of methods affected classification for a specific observation, while the more suitable classifier varied among sensors. This study underlines the compatibility issue in land use/cover mapping with different observations. © 2024 Copyright held by the owner/author(s).

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Prior Information Guided Semi-Supervised Semantic Segmentation of Remote Sensing Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Gan, Xiaorong Li, Wenting Zhang, Yongjun Long, Wei Lu, Yujie Chen, Ziyang Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou Guiyang550025 China University of Electronic Science and Technology of China School of Computer Science and Engineering College Chengdu611731 China Guizhou University of Commerce School of Computer and Information Engineering College Guizhou Guiyang550014 China

Remote sensing semantic segmentation has broad applications in critical fields such as urban planning and environmental monitoring. Semi-supervised semantic segmentation methods tackle the time and cost challenges of annotating remote sensing images by using abundant unlabeled data to optimize the model. Many existing semi-supervised methods generate pseudo-labels by inputting unlabeled data into the network, and then use these labels to progressively improve the model’s segmentation performance. However, the imbalanced class distribution and complex spatial layout of remote sensing images may result in unreliable pseudo-labels generated by the networks. To address this issue, we propose a Prior Information Guided Network (PGNet) that integrates a Prior Feature Guided Module (PFGM) for reliable feature priors and a Prior Edge Extraction Module (PEEM) to provide edge prior information. By leveraging the lightweight Segment Anything Model (SAM), PGNet enhances the ability to extract valuable information from unlabeled data, enabling the generation of more reliable pseudo-label. The PFGM employs Symmetric Cross-Attention to more balancedly integrate the SAM prior features with the semantic features from the encoder. Additionally, the PEEM employs SAM to extract reliable edge priors from unlabeled data, guiding the feature maps during training for more accurate segmentation boundaries. We conducted extensive experiments on the ISPRS Vaihingen, ISPRS Potsdam, and LoveDA datasets. The results demonstrate that our PGNet outperforms existing state-of-the-art semi-supervised methods. © 1980-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Quantum partial least squares regression algorithm for multiple correlation problem

引用

Chinese Physics B 2022年第3期31卷 177-186页

作者： Yan-Yan Hou Jian Li Xiu-Bo Chen Yuan Tian School of Artificial Intelligence Beijing University of Post and TelecommunicationsBeijing 100876China College of Information Science and Engineering Zaozhuang UniversityZaozhuang 277160China Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Post and TelecommunicationsBeijing 100876China GuiZhou University Guizhou Provincial Key Laboratory of Public Big DataGuiyang 550025China

Partial least squares(PLS) regression is an important linear regression method that efficiently addresses the multiple correlation problem by combining principal component analysis and multiple regression. In this paper, we present a quantum partial least squares(QPLS) regression algorithm. To solve the high time complexity of the PLS regression, we design a quantum eigenvector search method to speed up principal components and regression parameters construction. Meanwhile, we give a density matrix product method to avoid multiple access to quantum random access memory(QRAM)during building residual matrices. The time and space complexities of the QPLS regression are logarithmic in the independent variable dimension n, the dependent variable dimension w, and the number of variables m. This algorithm achieves exponential speed-ups over the PLS regression on n, m, and w. In addition, the QPLS regression inspires us to explore more potential quantum machine learning applications in future works.

关键词： quantum machine learning partial least squares regression eigenvalue decomposition

来源：评论

学校读者我要写书评

暂无评论

Dynamic and Real-Time Frame Rendering for Edge Computing-Enabled Metaverse Systems

Dynamic and Real-Time Frame Rendering for Edge Computing-Ena...

引用

IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

作者： Yuxin Li Ya Li Jianhang Tang Kebing Jin Yang Zhang Shaobo Li College of Computer Science and Technology Guizhou University China State Key Laboratory of Public Big Data Guizhou University China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China Guizhou Institute of Technology China

ISBN: (数字)9798350361704

ISBN: (纸本)9798350361711

Metaverse is an immersive, seamless, interactive, and comprehensive virtual world, as well as a replication, extension, and transcendence of the real world. The constantly improving image resolution and enriched scene details of Meta-verse applications have increased complexity and difficulty in rendering Metaverse panoramic frames. However, due to factors such as device computing, communication, and battery power, existing Metaverse scene rendering methods are unable to meet the high-quality rendering task requirements of users, resulting in image lag, high rendering latency, and reduced user experience quality. In this paper, through the collaborative use of the computation resources provided by edge servers and terminal devices, we propose a multi-terminal collaborative adaptive meta-universe panoramic frame rendering method, in which the gradient provided by model-based meta boundary rendering problem is used to generate integer rendering decisions using a Deep Reinforcement learning-based Frame Rendering (DRFR) framework. The meta-universe rendering task is decomposed and deployed to different computing platforms for execution. Comprehensive simulation results demonstrate that the DRFR model can reduce the Metaverse frame rendering time and improve user experience.

关键词： Wireless communication Metaverse Simulation Computational modeling Collaboration Reinforcement learning Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

A Sketch-Based Generation Model for Diverse Ceramic Tile Images Using Generative Adversarial Network

引用

Intelligent Automation & Soft Computing 2023年第9期37卷 2865-2882页

作者： Jianfeng Lu Xinyi Liu Mengtao Shi Chen Cui Mahmoud Emam School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310000China Faculty of Artificial Intelligence Menoufia UniversityShebin El-Koom32511Egypt

Ceramic tiles are one of the most indispensable materials for interior *** ceramic patterns can’t match the design requirements in terms of diversity and interactivity due to their natural *** this paper,we propose a sketch-based generation method for generating diverse ceramic tile images based on a hand-drawn sketches using Generative Adversarial Network(GAN).The generated tile images can be tailored to meet the specific needs of the user for the tile *** proposed method consists of four ***,a dataset of ceramic tile images with diverse distributions is created and then pre-trained based on ***,for each ceramic tile image in the dataset,the corresponding sketch image is generated and then the mapping relationship between the images is trained based on a sketch extraction network using ResNet Block and jump connection to improve the quality of the generated ***,the sketch style is redefined according to the characteristics of the ceramic tile images and then double cross-domain adversarial loss functions are employed to guide the ceramic tile generation network for fitting in the direction of the sketch style and to improve the training ***,we apply hidden space perturbation and interpolation for further enriching the output textures style and satisfying the concept of“one style with multiple faces”.We conduct the training process of the proposed generation network on 2583 ceramic tile images *** measure the generative diversity and quality,we use Frechet Inception Distance(FID)and Blind/Referenceless Image Spatial Quality Evaluator(BRISQUE)*** experimental results prove that the proposed model greatly enhances the generation results of the ceramic tile images,with FID of 32.47 and BRISQUE of 28.44.

关键词： Ceramic tile pattern design cross-domain learning deep learning GAN generative adversarial networks ResNet Block

来源：评论

学校读者我要写书评

暂无评论

Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning

arXiv

引用

arXiv 2024年

作者： Yao, He Zhang, Yongjun Jian, Huachun Zhang, Li Cheng, Ruzhong State Key Laboratory of Public Big Data Institute for Artificial Intelligence College of Computer Science and Technology Guizhou University Guizhou China North China Institute of Science and Technology Beijing China

The significance of background information is frequently overlooked in contemporary research concerning channel attention mechanisms. This study addresses the issue of suboptimal single-spectral nighttime pedestrian detection performance under low-light conditions by incorporating background information into the channel attention mechanism. Despite numerous studies focusing on the development of efficient channel attention mechanisms, the relevance of background information has been largely disregarded. By adopting a contrast learning approach, we reexamine channel attention with regard to pedestrian objects and background information for nighttime pedestrian detection, resulting in the proposed Fore-Background Contrast Attention (FBCA). FBCA possesses two primary attributes: (1) channel descriptors form remote dependencies with global spatial feature information;(2) the integration of background information enhances the distinction between channels concentrating on low-light pedestrian features and those focusing on background information. Consequently, the acquired channel descriptors exhibit a higher semantic level and spatial accuracy. Experimental outcomes demonstrate that FBCA significantly outperforms existing methods in single-spectral nighttime pedestrian detection, achieving state-of-the-art results on the NightOwls and TJU-DHD-pedestrian datasets. Furthermore, this methodology also yields performance improvements for the multispectral LLVIP dataset. These findings indicate that integrating background information into the channel attention mechanism effectively mitigates detector performance degradation caused by illumination factors in nighttime scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Communication channels (information theory)

来源：评论

学校读者我要写书评

暂无评论

Cohetrec: A Recommendation for Collaborative Heterogeneous Information Network

SSRN

引用

SSRN 2024年

作者： Chen, Yao Chen, Yuling Sang, Haiwei Dou, Hui Zhang, Yangwen State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Guizhou Education University Guiyang550018 China

Recommender Systems (RS) aim to predict the latent interests of users in items by leveraging embedding learning from user-item graphs. Graph Neural Networks (GNN) have significantly contributed to RS by enabling the learning of embeddings. However, relying solely on user-item interactions poses limitations, such as the cold-start problem. Social recommendation has gained attention for its potential to improve recommendation outcomes by incorporating social information among users. But, existing social-aware recommendation models have not adequately considered collaborative semantics among items. This paper addresses these limitations by proposing CoHetRec, a recommendation model that leverages GNN and a Collaborative Heterogeneous Information Network (CHIN) with latent collaborative heterogeneous relation factors. CoHetRec preserves factorized representations to capture diverse connections between users and items. It also introduces an attention-enhanced message propagation and aggregation scheme for heterogeneous relations in GNN, enabling the extraction of recursive heterogeneous semantic collaborations. Extensive experiments on three benchmark datasets demonstrate the superiority of CoHetRec over 15 state-of-the-art (SOTA) recommendation techniques. The highest average improvement is 31.88% for HR@5 and 38.39% for NDCG@5. And compared with the best performing method in the baseline on the Ciao dataset, our model improved HR@5 by 6.84%, NDCG@5 by 7.79%, while reducing the training time by 38.64%. © 2024, The Authors. All rights reserved.

关键词： Semantics

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：