检索结果-内蒙古大学图书馆

FDBPL: Faster distillation-based prompt learning for region-aware vision-language models adaptation

Expert Systems with Applications 2025年 293卷

作者： Zherui Zhang Jiaxin Wu Changwei Wang Rongtao Xu Longzhao Huang Wenhao Xu Wenbo Xu Li Guo Shibiao Xu School of Artificial Intelligence Beijing University of Posts and Telecommunications Haidian China School of National Elite Institute of Engineering Chongqing University Chongqing China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely heavily on task-specific hard labels, limiting their generalization to unseen categories. Recent popular distillation-based prompt learning methods improve generalization by exploiting larger teacher VLMs and unsupervised knowledge transfer, yet their repetitive teacher model online inference sacrifices the inherent training efficiency advantage of prompt learning. In this paper, we propose F aster D istillation- B ased P rompt L earning ( FDBPL ), which addresses these issues by sharing soft supervision contexts across multiple training stages and implementing accelerated I/O. Furthermore, FDBPL introduces a region-aware prompt learning paradigm with dual positive-negative prompt spaces to fully exploit randomly cropped regions that containing multi-level information. We propose a positive-negative space mutual learning mechanism based on similarity-difference learning, enabling student CLIP models to recognize correct semantics while learning to reject weakly related concepts, thereby improving zero-shot performance. Unlike existing distillation-based prompt learning methods that sacrifice parameter efficiency for generalization, FDBPL maintains dual advantages of parameter efficiency and strong downstream generalization. Comprehensive evaluations across 11 datasets demonstrate superior performance in base-to-new generalization, cross-dataset transfer, and robustness tests, achieving 2.2 × faster training speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Fault Diagnosis Method for Rolling Bearing Based on Attention and CNN

A Hybrid Fault Diagnosis Method for Rolling Bearing Based on...

引用

Robotics, Intelligent Control and Artificial Intelligence (RICAI), International Conference on

作者： Songtao Wang Qianlong Liu Jun Li Kun Liang Hui Cai Hangwei Tian Shandong Hi-Speed Construction Management Group Co. Ltd. Jinan China SHANDONG SCICOM Information and Economy Research Institute Co. Ltd. Jinan China Shandong Hi-Speed Group Linteng Highway Co. Ltd. Jinan China School of Qilu Transportation Shandong University Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

In the field of mechanical manufacturing, rolling bearings are important core components. To achieve stable rotational operation, improving diagnostic accuracy has become an urgent issue. In this paper, a hybrid fault diagnosis method is proposed, which combines attention and convolutional neural network and introduces Savitzky-Golay filter, called Savitzky-Golay Convolutional Attention network (SGCA-Net). The method adopts a dual-branch structure for rolling bearing fault diagnosis, which can effectively eliminate noise, and combines attention mechanism and convolutional neural network to perform feature learning on data. The experimental results show that the proposed method can accurately identify various faults, and has high accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AirDIV: Over-the-Air Cloud-Fog Data Integrity Verification Scheme for Industrial Cyber-Physical Systems

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Zhao, Yao Xiang, Yong Uddin, Md Palash Zhang, Yushu Liu, Lu Liu, Yansong Gao, Longxiang Deakin University School of Information Technology VIC Australia Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Nanchang330013 China University of Exeter Department of Computer Science Exeter United Kingdom RWTH Aachen University Department of Computer Science Aachen Germany Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China

Industrial Cyber-Physical Systems (ICPSs) have been motivating various Industry 4.0 endeavours, particularly with the integration of fog computing. Cloud-fog data caching paradigms, as supportive elements of ICPSs, have been adopted to cache user data, catering to diverse ICPS requirements such as data sensitivity and reduced access latency. In this hierarchical caching context, ensuring Cloud-Fog Data Integrity (CFDI) is crucial for maintaining the consistent functionality of ICPSs. Existing solutions primarily focus on examining the integrity of data cached solely on either cloud or fog nodes. However, cloud-cached data and fog-cached data are tightly coupled and should be considered simultaneously when checking data integrity. In this work, we introduce an over-the-air CFDI verification scheme, namely AirDIV, with a high accuracy and security guarantee. Instead of aggregating integrity proofs after proof transmission, AirDIV completes proof aggregation and transmission over the air for efficiency improvement. To enhance practicability, we derive adjustable parameters and formulate an optimization problem to minimize over-the-air aggregation errors. Furthermore, with an effective proof generation method, AirDIV can defend against two common attacks, i.e., replay and forge attacks. We provide a theoretical analysis of AirDIV's correctness, accuracy and security, while conducting extensive experiments on both simulated and real platforms to validate its efficiency. © 1983-2012 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

MINDFLOW: A network TRAFFIC ANOMALY DETECTION MODEL BASED ON MINDSPORE

arXiv

引用

arXiv 2025年

作者： Xiang, Qiuyan Wu, Shuang Wu, Dongze Liu, Yuxin Qin, Zhenkai School of Information Technology Guangxi Police College 530028 China College of Computer Science and AI Southwest Minzu University 610213 China Institute of Software Chinese Academy of Sciences 100190 China School of Computing and Information China Network Security Research Center China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China

With the wide application of IoT and industrial IoT technologies, the network structure is becoming more and more complex, and the traffic scale is growing rapidly, which makes the traditional security protection mechanism face serious challenges in dealing with high-frequency, diversified, and stealthy cyber-attacks. To address this problem, this study proposes MindFlow, a multi-dimensional dynamic traffic prediction and anomaly detection system combining convolutional neural network (CNN) and bi-directional long and short-term memory network (BiLSTM) architectures based on the MindSpore framework, and conducts systematic experiments on the NF-BoT-IoT dataset. The experimental results show that the proposed model achieves 99% in key metrics such as accuracy, precision, recall and F1 score, effectively verifying its accuracy and robustness in network intrusion detection. © 2025, CC0.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Computational strategy of dynamic nanorod networks for dielectric elastomer nanocomposites towards the balance of high permittivity, low modulus, and high breakdown strength

引用

Polymer 2025年 333卷

作者： Han Qin Yancong Feng Tao Liu Baofeng Gao Ying Guo Jingshan Pan Ming Tian Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250000 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan 250000 China Guangdong Provincial Key Laboratory of Optical Information Materials and Technology & Institute of Electronic Paper Displays South China Academy of Advanced Optoelectronics South China Normal University Guangzhou 510006 China State Key Laboratory of Organic-Inorganic Composites College of Materials Science and Engineering Beijing University of Chemical Technology Beijing 100029 China

Dielectric elastomers exhibit immense potential in emerging fields such as soft robotics, flexible sensors, wearable electronic devices, and energy harvesting, but their widespread application is limited by the intricate paradoxes among the high permittivity, low modulus, and high breakdown strength. By regulating the aspect ratio, concentration, interaction strength, and crosslinking density, a dynamic nanorod network structure is constructed to harmonize comprehensive properties. The construction of the nanorod network significantly enhances permittivity due to the coupling effect of nanorods. Meanwhile, the low percolation threshold avoids high modulus, enabling large electro-induced strain. Under high strain, nanorod orientation shifts, leading to the destruction of the network, thereby avoiding the electric field concentration and achieving the enhancement of electromechanical stability. After the external field is withdrawn, entropic elasticity drives the recovery of elastomers, while the network reconstructs to restore the high dielectric constant. This strategy offers new insights into balancing high permittivity, low modulus, and high breakdown strength in practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition

arXiv

引用

arXiv 2025年

作者： Wang, Changwei Chen, Shunpeng Song, Yukun Xu, Rongtao Zhang, Zherui Zhang, Jiguang Yang, Haoran Zhang, Yu Fu, Kexue Du, Shide Xu, Zhiwei Gao, Longxiang Guo, Li Xu, Shibiao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science China MAIS Institute of Automation Chinese Academy of Sciences China Tongji University China College of Computer and Data Science Fuzhou University China Shandong University China

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Deep Co-training for Semi-supervised Medical Image Segmentation

arXiv

引用

arXiv 2021年

作者： Zheng, Xu Fu, Chong Xie, Haoyu Chen, Jialei Wang, Xingwei Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Computer Science The University of Auckland New Zealand

Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segmentation tasks. Existing semi-supervised approaches enhance the ability to extract features from unlabeled data with prior knowledge obtained from limited labeled data. However, due to the scarcity of labeled data, the features extracted by the models are limited in supervised learning, and the quality of predictions for unlabeled data also cannot be guaranteed. Both will impede consistency training. To this end, we proposed a novel uncertainty-aware scheme to make models learn regions purposefully. Specifically, we employ Monte Carlo Sampling as an estimation method to attain an uncertainty map, which can serve as a weight for losses to force the models to focus on the valuable region according to the characteristics of supervised learning and unsupervised learning. Simultaneously, in the backward process, we joint unsupervised and supervised losses to accelerate the convergence of the network via enhancing the gradient flow between different tasks. Quantitatively, we conduct extensive experiments on three challenging medical datasets. Experimental results show desirable improvements to state-of-the-art counterparts. Copyright © 2021, 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

Integrated Multi-featured Android Malicious Code Detection

Integrated Multi-featured Android Malicious Code Detection

引用

2019国际计算机前沿大会

作者： Qing Yu Hui Zhao Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology

To solve the problem that using a single feature cannot play the role of multiple features of Android application in malicious code detection,an Android malicious code detection mechanism is proposed based on integrated learning on the basis of dynamic and static *** three types of Android behavior characteristics,a three-layer hybrid algorithm was *** it combined the malicious code detection based on digital signature to improve the detection *** digital signature of the known malicious code was extracted to form a malicious sample *** authority that can reflect Android malicious behavior,API call and the running system call features were also *** expandable hybrid discriminant algorithm was designed for the above three types of *** algorithm was tested with machine learning method by constructing the optimal classifier suitable for the above ***,the Android malicious code detection system was designed and implemented based on the multi-layer hybrid *** experimental results show that the system performs Android malicious code detection based on the combination of signature and dynamic and static *** with other related work,the system has better performance in execution efficiency and detection rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical Calculation of Partial Differential Equation Deduction in Adaptive Total Variation Image Denoising

Numerical Calculation of Partial Differential Equation Deduc...

引用

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics

作者： Minghua Zhao Qin Wang Abdul Nasir Muniru Jiawei Ning Peng Li Bing Li Shaanxi Key Laboratory of Network Computing and Security Technology Xi'an Shaanxi China

Total variation model of image denoising is easy to influence the gradient and lose the details of image. Due to these weaknesses, many adaptive total variation (ATV) models of image denoising have been proposed to eliminate the Gaussian noisy additive in the image. This paper implements the model through a numerical solution, where the gradient descent method is used to derive the partial differential equation (PDE) corresponding to the ATV model. First, based on Euler-Lagrange equation, a detailed derivation process for Partial Differential Equation is used to calculate the ATV model. Then, based on gradient descent method, a numerical calculation of the model is derived from the PDE using the Direct Difference Method. Finally, several different λ parameters are compared to produce different image denoising effects and the appropriate parameter λ value is determined. Experimental results prove that our proposed numerical calculation can effectively realize the ATV denoising model.

关键词： Mathematical model Numerical models Adaptation models Image denoising Noise reduction TV Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

On the ADEP and DOR Analysis of RIS-aided URLLC Systems with Partial CSI in Smart Factory

On the ADEP and DOR Analysis of RIS-aided URLLC Systems with...

引用

IEEE Globecom Workshops

作者： Tingnan Bao Haiming Wang Hong-Chuan Yang Wen-Jing Wang Mazen O. Hasna Lenovo Research + Institute Of Computing Technology Chinese Academy of Sciences Beijing China Lenovo Reseach Lenovo Group Limited Bejiing China Department of Electrical and Computer Engineering University of Victoria Victoria Canada Shaanxi Key Laboratory of Information Communication Network and Security XUPT Xi'an China Department of Electrical Engineering Qatar University Doha Qatar

ISBN: (数字)9781665423908

ISBN: (纸本)9781665423915

Factory automation applications impose stringent quality of service (QoS) over ultra-reliable and low-latency communication (URLLC) system. However, the existing wireless systems cannot meet the requirement for these mission-critical industrial internet-of-things (IIoT) applications. In this paper, we consider the reconfigurable intelligent surface (RIS)-aided URLLC systems in the smart factory. To facilitate the performance analysis of the practical situation, the presence of phase error at RIS is discussed. We analyze and derive approximate closed-form expression of average decoding error probability (ADEP) and the closed-form expression of performance limits de-lay outage rate (DOR) under our proposed scenario, respectively. Through analytical results and associated numerical examples, we demonstrate the effect of the number of reflecting elements at the RIS, channel blocklength and packet size in achieving high reliability and low latency. Therefore, the deployment of RIS can offer an attractive solution to enhance the reliability over URLLC systems in the smart factory.

关键词： Wireless communication Closed-form solutions Error probability Rician channels Quality of service Ultra reliable low latency communication Reconfigurable intelligent surfaces

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：