检索结果-内蒙古大学图书馆

DSAFF-Net:A Backbone Network Based on Mask R-CNN for Small Object Detection

Computers, Materials & Continua 2023年第2期74卷 3405-3419页

作者： Jian Peng Yifang Zhao Dengyong Zhang Feng Li Arun Kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India

Recently,object detection based on convolutional neural networks(CNNs)has developed *** backbone networks for basic feature extraction are an important component of the whole detection ***,we present a new feature extraction strategy in this paper,which name is *** this strategy,we design:1)a sandwich attention feature fusion module(SAFF module).Its purpose is to enhance the semantic information of shallow features and resolution of deep features,which is beneficial to small object detection after feature fusion.2)to add a new stage called D-block to alleviate the disadvantages of decreasing spatial resolution when the pooling layer increases the receptive *** method proposed in the new stage replaces the original method of obtaining the P6 feature map and uses the result as the input of the regional proposal network(RPN).In the experimental phase,we use the new strategy to extract *** experiment takes the public dataset of Microsoft Common Objects in Context(MS COCO)object detection and the dataset of Corona Virus Disease 2019(COVID-19)image classification as the experimental object *** results show that the average recognition accuracy of COVID-19 in the classification dataset is improved to 98.163%,and small object detection in object detection tasks is improved by 4.0%.

关键词： Small object detection classification RPN MS COCO COVID-19

来源：评论

学校读者我要写书评

暂无评论

A study of MySQL protocol-based database proxy approval system for fortress machine

引用

International Journal of data Science 2025年第1期10卷 96-117页

作者： Zhang, Xian Luo, Xinhui Yin, Dong Qu, Taiguo Li, Hao Huaihua University Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Huaihua Tourism School Hunan Huaihua418099 China

With the increase of enterprise informatisation, database security and compliance operation management have become increasingly important. Therefore, it is essential to design an efficient database proxy approval system. In this paper, we develop a database proxy approval system based on the MySQL protocol for fortress machines, which provides a real-time customised configuration scheme for high-risk commands, designs a real-time approval process for six types of high-risk commands, and creates a simple and efficient matching algorithm for high-risk commands. We designed a large number of experiments to test the system’s connection success rate, operation stability, response time, CPU resource consumption, matching algorithm performance, and other aspects. The experimental results show that this database proxy approval system has good configuration flexibility, high accuracy, and good time performance. This system has a wide range of applications in electric power, finance, petroleum, and other fields. © 2025 Inderscience Enterprises Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking-based Code Summarization with Chain of Comments 31

Rethinking-based Code Summarization with Chain of Comments

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Liuwen He, Hongkui Huang, Hailin Wang, Jiexin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9798891761964

Automatic code summarization aims to generate concise natural language descriptions (summary) for source code, which can free software developers from the heavy burden of manual commenting and software maintenance. Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the significant heterogeneity gap between code and summary. Moreover, existing methods lack a human-like re-check process to evaluate whether the generated summaries match well with the code. To address these two limitations, we introduce RBCoSum, a novel framework that incorporates the generated Chain Of Comments (COC) as auxiliary intermediate information for the model to bridge the gap between code and summaries. Also, we propose a rethinking process where a learned ranker trained on our constructed ranking dataset scores the extent of matching between the generated summary and the code, selecting the highest-scoring summary to achieve a re-check process. We conduct extensive experiments to evaluate our approach and compare it with other automatic code summarization models as well as multiple code Large Language Models (LLMs). The experimental results show that RBCoSum is effective and outperforms baselines by a large margin. The human evaluation also proves the summaries generated with RBCoSum are more natural, informative, useful, and truthful. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Unified pre-training with pseudo infrared images for visible-infrared person re-identification

引用

Multimedia Tools and Applications 2024年第38期83卷 86039-86058页

作者： Liu, ZhiGang Hu, Yan College of Computer and Information Technology Northeast Petroleum University Heilongjiang Daqing163318 China Heilongjiang Petroleum Big data and Intelligent Analysis Key Laboratory Northeast Petroleum University Heilongjiang Daqing163318 China

In the pre-training task of visible-infrared person re-identification(VI-ReID), two main challenges arise: i) Domain disparities. A significant domain gap exists between the ImageNet utilized in public pre-trained models and the specific person data in the VI-ReID task. ii) Insufficient sample. Due to the challenge of gathering cross-modal paired samples, there is currently a scarcity of large-scale datasets suitable for pretraininge. To address the aforementioned issues, we propose a new unified pre-training framework (UPPI). Firstly, we established a large-scale visible-pseudo infrared paired sample repository (UnitCP) based on the existing visible person dataset, encompassing nearly 170,000 sample pairs. Benefiting from this repository, not only are training samples significantly expanded, but pre-training on this foundation also effectively bridges the domain disparities. Simultaneously, to fully harness the potential of the repository, we devised an innovative feature fusion mechanism(CF2) during pre-training. It leverages redundant features present in the paired images to steer the model towards cross-modal feature fusion. In addition, during fine-tuning, to adapt the model to datasets lacking paired images, we introduced a center contrast loss(C2). This loss guides the model to prioritize cross-modal features with consistent identities. Extensive experimental results on two standard benchmarks (SYSU-MM01 and RegDB) demonstrate that the proposed UPPI performs favorably against state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Some Thoughts on the Classification Standard of intelligent Autonomous Level of Measurement and Control System 9

Some Thoughts on the Classification Standard of Intelligent ...

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Yuan, Guangfu Yang, Liu Han, Haoran Li, Yong Shao, Cong Zhan, Siyu Gansu Photoelectric Measurement Technology Research Laboratory Gansu735018 China University of Electronic Science and Technology of China Laboratory of Intelligent Collaborative Computing Chengdu China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu611731 China

ISBN: (纸本)9798350330076

Intelligence is an important trend in the development of measurement and control systems. However, there is still a lack of unified understanding of the intelligent autonomous classification of the measurement and control system. The establishment of intelligent evaluation standards in this field has become an urgent research topic. This paper first gives an overview of the aviation measurement and control system, and then takes the classification standards of autonomy in the fields of automobile driving automation in China and the United states, the autonomy and autonomy level of typical ships in China, and the automation of civil unmanned aircraft system in China as a reference. A 5-level intelligent grading standard based on task adaptability, environmental complexity and human-computer interaction is proposed. The classification standard is practical and easy to understand. It can provide reference for the establishment of intelligent standards for measurement and control systems, improve the application speed of intelligent autonomous technology in the field of measurement and control, and broaden the application prospect of intelligent measurement and control systems. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

TOWARDS ROBUST AND EFFICIENT CLOUD-EDGE ELASTIC MODEL ADAPTATION VIA SELECTIVE ENTROPY DISTILLATION 12

TOWARDS ROBUST AND EFFICIENT CLOUD-EDGE ELASTIC MODEL ADAPTA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Chen, Yaofo Niu, Shuaicheng Wang, Yaowei Xu, Shoukai Song, Hengjie Tan, Mingkui South China University of Technology China Pengcheng Laboratory China Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Laboratory China

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for some period) due to the potential high cost of model adaptation for both the server and edge sides. However, in many real-world scenarios, the test environments may change dynamically (known as distribution shifts), which often results in degraded performance. Thus, one has to adapt the edge models promptly to attain promising performance. Moreover, with the increasing data collected at the edge, this paradigm also fails to further adapt the cloud model for better performance. To address these, we encounter two primary challenges: 1) the edge model has limited computation power and may only support forward propagation;2) the data transmission budget between cloud and edge devices is limited in latency-sensitive scenarios. In this paper, we establish a Cloud-Edge Elastic Model Adaptation (CEMA) paradigm in which the edge models only need to perform forward propagation and the edge models can be adapted online. In our CEMA, to reduce the communication burden, we devise two criteria to exclude unnecessary samples from uploading to the cloud, i.e., dynamic unreliable and low-informative sample exclusion. Based on the uploaded samples, we update and distribute the affine parameters of normalization layers by distilling from the stronger foundation model to the edge model with a sample replay strategy. Extensive experimental results on ImageNet-C and ImageNet-R verify the effectiveness of our CEMA. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

DDoS Detection and Defense Based on FLAD and SDN 20

DDoS Detection and Defense Based on FLAD and SDN

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Dong, Jie Fang, Wenyu Zheng, Wanling Liu, Jinkun Liu, Yanhua College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China

ISBN: (纸本)9798350356328

In order to achieve more efficient and accurate DDoS detection while ensuring data privacy, this paper proposes a DDoS detection method based on FLAD. Firstly, this paper uses the FLAD algorithm to train a global DDoS detection model without leaving local traffic data, protecting the privacy and security of traffic data between different hosts, and improving aggregation efficiency by dynamically adjusting the aggregation weights to adapt to different sub-dataset increments. Secondly, a DDoS traffic detection method based on the integration of LSTM and CNN is proposed, which extracts and analyzes the temporal correlation of traffic data by calculating the statistical characteristics of traffic data within a time period, to achieve real-time detection of traffic feature data. Again, combined with the concept of SDN, real-time defense against DDoS based on ODL-API is implemented, and precise matching of DDoS detection results with network entity information is achieved, realizing the technology of real-time and precise issuance of multiple flow rules, effectively blocking DDoS malicious attack traffic, protecting important entities in the topology, and maintaining stable traffic in the topology. This paper focuses on solving the detection problem of DDoS traffic data increments and uneven data distribution through the FLAD algorithm. Experimental results show that the proposed method improves the accuracy of DDoS attack detection by more than 4% and the F1 Score by more than 7% compared to the FedAvg aggregation algorithm. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model

引用

Plant Phenomics 2023年第3期5卷 501-519页

作者： Qianding Huang Xingcai Wu Qi Wang Xinyu Dong Yongbin Qin Xue Wu Yangyang Gao Gefei Hao State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang 550025China National Key Laboratory of Green Pesticide Guizhou UniversityGuiyang 550025China

Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food *** detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating ***,existing methods are still limited to single crop disease *** importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile ***,reducing the number of model parameters tends to cause a decrease in model *** solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple *** detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher *** develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing ***,the multistage knowledge distillation technique can make the model lighter while maintaining high *** only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart *** code is available at https://***/QDH/MSKD.

关键词： Plant diagnosis image

来源：评论

学校读者我要写书评

暂无评论

Resolution-Adaptive Representation Learning via Eliminating Abnormal Features for Cross-Resolution Person Re-Identification 14

Resolution-Adaptive Representation Learning via Eliminating ...

引用

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Lu, Xing Lai, Fengshan Cao, Zhixiang Xia, Daoxun Guizhou Normal University School of Big Data and Computer Science Guiyang China Guizhou Normal University Key Laboratory of Information and Computing Science Guizhou Province Guiyang China Guizhou Normal University Engineering Laboratory for Applied Technology of Big Data in Education Guiyang China

ISBN: (纸本)9798350356670

Cross-resolution person re-identification(CR-ReID) seeks to overcome the challenge of retrieving and matching specific person images across cameras with varying resolutions. Numerous existing studies utilize established CNNs and ViTs models to resize captured low-resolution (LR) images and align them with high-resolution (HR) image features. However, these methods overlook the potential feature connections between LR and HR images. Consequently, CNNs or ViTs tend to highlight outliers rather than the intended characteristics in LR image attention maps. In this work, we propose the abnormal feature elimination and reconfiguration transformer (ART) network, a novel network architecture, for robust cross-resolution person re-identification tasks. Our proposed method uses a resolution feature discriminator to learn resolution invariant features and outputs feature matrices of images with different resolutions. We utilize output feature matrices to model LR and HR image interactions through cross-resolution landmark agent attention. We aim to mitigate abnormal image features and prioritize the attention on the target person by learning representations from input images of various resolutions. Extensive evaluations on three real-world datasets confirm the excellent results of our approach. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

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：