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

Automated Controller Placement for Software-Defined Networks to Resist DDoS Attacks

引用

computers, Materials & Continua 2021年第9期68卷 3147-3165页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Lee Ching Kwang Rizaludin Kaspin Bhawani Shankar Chowdhry Rajkumar Buyya Satya Prasad Majumder Manoj Gupta Shuaib Memon Faculty of Computing&Informatics Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation CentreCyberjaya63000SelangorMalaysia National Center of Robotics and Automation Mehran University of Engineering&TechnologyJamshoroPakistan Department of Computer Science and Engineering Hanyang UniversitySeoul04763South Korea School of Electrical and Electronic Engineering Nanyang Technological University639798Singapore Cloud Computing and Distributed Systems Laboratory The University of MelbourneMelbourneVIC 3053Australia Department of Electrical and Electronic Engineering Bangladesh University of Engineering and Technology(BUET)Dhaka1205Bangladesh Department of Electronics and Communication Engineering JECRC UniversityVidhaniJaipur303905India Auckland Institute of Studies Mt AlbertAucklandNew Zealand

In software-defined networks(SDNs),controller placement is a critical factor in the design and planning for the future Internet of Things(IoT),telecommunication,and satellite communication *** research has concentrated largely on factors such as reliability,latency,controller capacity,propagation delay,and energy ***,SDNs are vulnerable to distributed denial of service(DDoS)attacks that interfere with legitimate use of the *** ever-increasing frequency of DDoS attacks has made it necessary to consider them in network design,especially in critical applications such as military,health care,and financial services networks requiring high *** propose a mathematical model for planning the deployment of SDN smart backup controllers(SBCs)to preserve service in the presence of DDoS *** a number of input parameters,our model has two distinct ***,it determines the optimal number of primary controllers to place at specific locations or nodes under normal operating ***,it recommends an optimal number of smart backup controllers for use with different levels of DDoS *** goal of the model is to improve resistance to DDoS attacks while optimizing the overall cost based on the *** simulated results demonstrate that the model is useful in planning for SDN reliability in the presence of DDoS attacks while managing the overall cost.

关键词： SDN automated controller placement SBC ILP DDoS attack

来源：评论

学校读者我要写书评

暂无评论

Revocable and certificateless public auditing for cloud storage

引用

Science China(Information Sciences) 2020年第10期63卷 282-284页

作者： Yinghui ZHANG Tiantian ZHANG Shengmin XU Guowen XU Dong ZHENG School of Cyberspace Security Xi'an University of Posts and Telecommunications Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology National Engineering Laboratory for Wireless Security Xi'an University of Posts and Telecommunications Secure Mobile Centre School of Information SystemsSingapore Management University School of Computer Science and Engineering University of Electronic Science and Technology of China

Dear editor,Plenty of computing and storage resources in the cloud are provided for users with restricted computing and storage resources,which has attracted the attention of many researchers[1,2].A generic blockchain-based cloud data auditing scheme[3] is proposed,which is compatible with any blockchains including the bitcoin *** the data integrity checking scheme,certificate-

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network

arXiv

引用

arXiv 2021年

作者： Fang, Yuchen Qin, Yanjun Luo, Haiyong Zhao, Fang Xu, Bingbing Wang, Chenxing Zeng, Liang School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications China Research Center for Ubiquitous Computing Systems Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China Tsinghua University China

Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to three aspects: i) current existing works mostly exploit intricate temporal patterns (e.g., the short-term thunderstorm and long-term daily trends) within a single method, which fail to accurately capture spatio-temporal dependencies under different schemas;ii) the under-exploration of the graph positional encoding limit the extraction of spatial information in the commonly used full graph attention network;iii) the quadratic complexity of the full graph attention introduces heavy computational needs. To achieve the effective traffic flow forecasting, we propose an efficient spectral graph attention network with disentangled traffic sequences. Specifically, the discrete wavelet transform is leveraged to obtain the low- and high-frequency components of traffic sequences, and a dual-channel encoder is elaborately designed to accurately capture the spatio-temporal dependencies under long- and short-term schemas of the low- and high-frequency components. Moreover, a novel wavelet-based graph positional encoding and a query sampling strategy are introduced in our spectral graph attention to effectively guide message passing and efficiently calculate the attention. Extensive experiments on four real-world datasets show the superiority of our model, i.e., the higher traffic forecasting precision with lower computational cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

GradSA: Gradient Sparsification and Accumulation for Communication-Efficient Distributed Deep Learning 15th

GradSA: Gradient Sparsification and Accumulation for Communi...

引用

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Liu, Bo Jiang, Wenbin Zhao, Shaofeng Jin, Hai He, Bingsheng National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Huazhong University of Science and Technology Wuhan China Library Henan University of Economics and Law Zhengzhou China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9783030642426

Large-scale distributed deep learning is of great importance in various applications. For distributed training, the inter-node gradient communication often becomes the performance bottleneck. Gradient sparsification has been proposed to reduce the communication overhead. However, the sparsification only arbitrarily selects a small fraction of gradients, while the efficiency of selection dimension has been overlooked. Furthermore, gradient staleness is inevitable after applying the sparsification which will ultimately lead to model divergence. In this paper, we propose a staleness-compensated sparse stochastic gradient descent algorithm, GradSA, to improve the training efficiency. Layer-level gradients are sparsified to reduce the communication overhead, which conform to the characteristics of the network structure, and historical accumulation of the approximated gradients is utilized to speed up convergence. We demonstrate the model convergence acceleration and the efficiency of our layer-level selection over existing state-of-the-art works, such as DGC, TernGrad, and 8-Bit quantization. © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

PFV2: Packet fragmentation with variable size and vigorous mapping in time-sensitive networking

引用

Journal of systems Architecture 2025年 166卷

作者： Yan, Wenyan Fu, Bin Wei, Dongsheng Li, Renfa Lei, Yixue Jia, Yuhang Xie, Guoqi Key Laboratory for Embedded and Network Computing of Hunan Province College of Computer Science and Electronic Engineering Hunan University Hunan Changsha410082 China Center for Convergence of Automobile and Cyberspace Research Institute of Hunan University in Chongqing Chongqing401120 China Future Network Laboratory Tencent Beijing100080 China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems School of Computer and Artificial Intelligence Xiangnan University Hunan Chenzhou423000 China

With the rapid advancement of intelligent automobiles, the ever-growing communication data put forward high bandwidth and low latency requirements. To meet these requirements, automotive Original Equipment Manufacturers (OEMs) widely adopt domain-centralized Electrical/Electronic (E/E) architecture. In this architecture, Time-Sensitive Networking (TSN) is expected to serve as the backbone network because of its high bandwidth and deterministic communication. TSN uses the Gate Control List (GCL) to divide its time length into multiple time slots, and the time intervals of these time slots are non-uniform (equal or unequal). Different flows have varying requirements for time slot sizes. To enhance the acceptance ratio of Time-Triggered (TT) flows through GCL time slot allocation, packet fragmentation (i.e., flow fragmentation) is introduced into TSN in the recent study. The state-of-the-art packet fragmentation solution divides one un-schedulable TT flow into multiple equal-sized packets (i.e., equal-sized time slots). In other words, these fixed-size packets are difficult to be mapped into the time slots with different sizes. This study develops a Packet Fragmentation with Variable-size and Vigorous-mapping (PFV2) technique based on the following three innovations: (1) we implement variable-size packet fragmentation, which iteratively divides the un-schedulable TT flow into smaller packets and then dynamically reschedules these packets;(2) we implement the vigorous mapping solution from packets to time slots by deeply searching for available time slots within the flow's deadline;and (3) we verify PFV2 based on the LS1028A with Cortex-A72 (i.e., the NXP automotive-grade development board). PFV2 improves the acceptance ratio by up to 20.18% and bandwidth utilization by up to 7.024% compared with the state-of-the-art solution. The theoretical and practical co-verification experiments demonstrate that the PFV2 can effectively improve the flow acceptance ratio and outperf

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision

arXiv

引用

arXiv 2025年

作者： Han, Xiaofeng Chen, Shunpeng Fu, Zenghuang Feng, Zhe Fan, Lue An, Dong Wang, Changwei Guo, Li Meng, Weiliang Zhang, Xiaopeng Xu, Rongtao Xu, Shibiao The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center China

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We systematically review the applications of multimodal fusion in key robotic vision tasks, including semantic scene understanding, simultaneous localization and mapping (SLAM), 3D object detection, navigation and localization, and robot manipulation. We compare VLMs based on large language models (LLMs) with traditional multimodal fusion methods, analyzing their advantages, limitations, and synergies. Additionally, we conduct an in-depth analysis of commonly used datasets, evaluating their applicability and challenges in real-world robotic scenarios. Furthermore, we identify critical research challenges such as cross-modal alignment, efficient fusion strategies, real-time deployment, and domain adaptation, and propose future research directions, including self-supervised learning for robust multimodal representations, transformer-based fusion architectures, and scalable multimodal frameworks. Through a comprehensive review, comparative analysis, and forward-looking discussion, we provide a valuable reference for advancing multimodal perception and interaction in robotic vision. A comprehensive list of studies in this survey is available at https://***/Xiaofeng-Han-Res/MF-RV. Copyright © 2025, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Inpainting of ultrasound cardiac tissues with consistent anatomical structures

引用

Biomedical Signal Processing and Control 2025年 110卷

作者： Honghe Li Jinzhu Yang Mei Wei Mingjun Qu Yong Feng Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China

Image inpainting techniques play a crucial role in restoring occluded regions in medical images, ultimately enhancing the consistency of clinical diagnoses. Traditional inpainting methods often face challenges when attempting to restore complex anatomical structures and large occluded areas in medical ultrasound images. While recent deep learning-based techniques show promise, they still encounter issues such as loss of edge information and inconsistent reconstruction in occluded regions. In this paper, we introduce a Segmentation-guided Medical Ultrasound Inpainting framework designed to overcome these limitations. Our framework integrates segmentation-derived edge priors to guide the inpainting process, ensuring anatomical consistency and enhancing the recovery of fine details. We propose a Multi-Scale Mixed Residual Block to improve the model’s ability to restore large masked regions and a Deformable Edge Attention mechanism to preserve critical edge details during downsampling while minimizing the introduction of noise. Extensive experiments on two publicly available echocardiography datasets show that our method significantly outperforms state-of-the-art inpainting models in terms of PSNR, MAE, and SSIM metrics. The results highlight the potential of our approach to provide accurate, consistent ultrasound image reconstruction, making it a valuable tool for clinical diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Network in Biomedical Image Segmentation

RCGA-Net: An Improved Multi-hybrid Attention Mechanism Netwo...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xiao, Feng Shen, Cong Chen, Yu Yang, Tian Chen, Shengyong Liao, Zhijun Tang, Jijun Tianjin University of Technology School of Computer Science and Engineering Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China School of Basic Medical Sciences Fujian Medical University Fujian Fuzhou China College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Systems Bioengineering Ministry of Education Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Department of Computer Science and Engineering University of South Carolina ColumbiaSC United States

ISBN: (纸本)9781665401265

Drawing support from an effective Medical Image Segmentation (MIS) is conducive to a substantial diagnostic basis for the physicians to identify the focus lesion in the patient body and give the subsequent clinical assessment of the patient status. Although various works have tried the challenging quantitative analysis problem, it is still difficult to conduct precise automatic segmentation, especially the soft tissue organs. In this decade, with the increased amount of available datasets, deep learning-based networks have achieved remarkable performance in image processing. Inspired by the state-of-the-art deep learning works, in this paper, we propose an end-to-end multi-layer network named RCGA-Net. It consists of an encoder-decoder backbone that integrates a coordinate attention mechanism based on space and channel and a global context extraction module to highlight more valuable information. To evaluate the performance of RCGA-Net, we apply it to different kinds of clinical and experimental MIS tasks to testify its generalization ability. Extensive experiments represent that our schema has taken the outperform or compatible results among the comparison methods group. Specifically, the numeric result of RCGA-Net on the pulmonary dataset has achieved a 99.12% optimum F1-score. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Regularly Truncated M-estimators for Learning with Noisy Labels

arXiv

引用

arXiv 2023年

作者： Xia, Xiaobo Lu, Pengqian Gong, Chen Han, Bo Yu, Jun Yu, Jun Liu, Tongliang The Sydney AI Center School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia The Australian AI Institute Faculty of Engineering and IT The University of Technology Sydney BroadwayNSW2007 Australia The PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University Hong Kong The Department of Computer Science Hong Kong Baptist University Hong Kong The School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China The Department of Automation University of Science and Technology of China Hefei230026 China

The sample selection approach is very popular in learning with noisy labels. As deep networks "learn pattern first", prior methods built on sample selection share a similar training procedure: the small-loss examples can be regarded as clean examples and used for helping generalization, while the large-loss examples are treated as mislabeled ones and excluded from network parameter updates. However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples;(b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization. In this paper, we propose regularly truncated M-estimators (RTME) to address the above two issues simultaneously. Specifically, RTME can alternately switch modes between truncated M-estimators and original M-estimators. The former can adaptively select small-losses examples without knowing the noise rate and reduce the side-effects of noisy labels in them. The latter makes the possibly clean examples but with large losses involved to help generalization. Theoretically, we demonstrate that our strategies are label-noise-tolerant. Empirically, comprehensive experimental results show that our method can outperform multiple baselines and is robust to broad noise types and levels. The implementation is available at https://***/xiaoboxia/RTM_LNL. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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：