检索结果-内蒙古大学图书馆

Stargan-based camera style transfer for person retrieval

International Journal of Information and Communication technology 2020年第1期16卷 1-16页

作者： Wang, Yuanyuan Wang, Zhijian Jiang, Mingxin College of Computer and Software Engineering Huaiyin Institute of Technology Huaian China College of Computer and Information Hohai University Nanjing China College of Electronic Information Engineering Huaiyin Institute of Technology Huaian China

Person retrieval is also known as person re-identification (ReID) aiming to match person among cross cameras. Although the results of the person ReID have performed well in small datasets, the issues of the large number of identities in real scenarios or with more cameras have not been fully investigated. Being an image retrieval task under cross multi-cameras of intelligent video security, person ReID is influenced by the image style change caused by different camera illumination and view angles. The number of cameras in the latest datasets is increasing and more camera transfer models need to be trained. Traditional methods of generative adversarial network (GAN) can only handle transfer of two domains. To facilitate the research towards solving these problems, we use star generative adversarial networks (StarGAN) to transfer the image from one camera to another camera in the latest large benchmark datasets. We train multiple transfer models simultaneously, minimising the bias among different cameras. Label smooth regularisation (LSR) algorithm is utilised to mitigate the effects of noise in the model. We learn part-based descriptors from pedestrian samples to generate robust feature representation. Our work is competitive compared to the state-of-the-art. © 2020 Inderscience Enterprises Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Phishing Url Detection: A Solution Based on Deep Learning Framework 18

Intelligent Phishing Url Detection: A Solution Based on Deep...

引用

18th International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2021

作者： Butt, Muhammad Hassaan Farooq Li, Jian Ping Saboor, Tehreem Arslan, Muhammad Butt, Muhammad Adnan Farooq University of Electronic Science and Technology of China School of Computer Science and Engineering China Shaheed Zulfikar Ali Bhutto Institute of Science and Technology Department of Computer Science Pakistan COMSATS University Islamabad Pakistan Foundation University Department of Software Engineering Pakistan

ISBN: (纸本)9781665413640

On the Internet, every different day, kinds of attacks are deployed on innocent users. Among all, phishing is the most severe attack in which users lose their credentials or private information and their financial status quickly. The attacker uses their credibility or sensitive information to harm the target or victim. The attacker is clever and uses different strategies to fetch user-sensitive information. The existing techniques fail to overcome these issues to some extent. This work focuses on discovering the essential features that help to differentiate the legitimate and illegitimate URLs. We applied a deep learning technique on the benchmark datasets to identify the pattern of phishing URLs. We used gradient boosted decision trees algorithm to train our model and applied the regular deeply connected neural network layers in various sequences and Adam optimizer. The most found patterns will help the system to detect phishing URLs and avoid phishing. We consider the accuracy, Ff-score, and Root Mean Square Error (RMSE) as our evaluation metrics for model evaluation. The results show that the trained model can achieve an approximately 92% accuracy and 94% f-score. © 2021 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Bilevel Progressive Homography Estimation Via Correlative Region-Focused Transformer

SSRN

引用

SSRN 2023年

作者： Jia, Qi Zhang, Wei Feng, Xiaomei Liu, Yu Pu, Nan Sebe, Nicu DUT School of Software Technology DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian116620 China Department of Information Engineering and Computer Science University of Trento Trento38122 Italy

We propose a novel correlative region-focused transformer for accurate homography estimation by a bilevel progressive architecture. Existing methods typically consider the entire image features to establish correlations for a pair of input images, but irrelevant regions often introduce mismatches and outliers. In contrast, our network effectively mitigates the negative impact of irrelevant regions through a bilevel progressive homography estimation architecture. Specifically, in the outer iteration, we progressively estimate the homography matrix at different feature scales;in the inner iteration, we dynamically extract correlative regions and progressively focus on their corresponding features from both inputs. Moreover, we develop a quadtree attention mechanism based on transformer to explicitly capture the correspondence between the input images, localizing and cropping the correlative regions for the next iteration. This progressive training strategy enhances feature consistency and enables precise alignment with comparable inference rate. Extensive experiments on qualitative and quantitative comparisons show that the proposed method reduces the mean average corner error (MACE) by about 55% on the MS-COCO dataset compared to previous methods, without increasing additional parameter cost. © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Transformer Topology for Distribution Network Voltage Regulation

A Hybrid Transformer Topology for Distribution Network Volta...

引用

2021 IEEE Southern Power Electronics Conference, SPEC 2021

作者： Power, Rupert Mithani, Alykhan Madawala, Udaya Baguley, Craig The University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Auckland University of Technology Department of Engineering Computing and Mathematical Sciences Auckland New Zealand

ISBN: (纸本)9781665436236

Worldwide, distributed generation sources are being installed in increasing numbers within distribution networks. This poses new challenges for distribution network operators, including voltage fluctuations beyond permissible limits that can differ in different parts of the same distribution network. The Hybrid Transformer (HT) is an effective solution that can mitigate voltage fluctuations continuously, dynamically and in a local manner, through combining a standard distribution transformer with a power electronic converter. In this paper a retrofittable HT topology is proposed. It utilises a second, fractionally-rated line frequency transformer (LFT) to enable the use of low-voltage power electronics with low power ratings for reduced costs and complexity. The proposed topology is modelled and a scaled hardware prototype is used to verify theory and simulation results. The simulation and experimental results show the efficacy of the proposed topology, its applicability to mitigate voltage fluctuations, and its benefits over alternative approaches. © 2021 IEEE.

关键词： Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Fast Second-order Method for Neural Networks under Small Treewidth Setting

Fast Second-order Method for Neural Networks under Small Tre...

引用

IEEE International Conference on Big Data

作者： Xiaoyu Li Jiangxuan Long Zhao Song Tianyi Zhou Department of Computer Science Stevens Institute of Technology Hoboken NJ School of Software Engineering South China University of Technology Guangzhou China The Simons Institute for the Theory of Computing University of California Berkeley Berkeley CA Department of Computer Science University of Southern California Los Angeles CA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Training neural networks is a fundamental problem in theoretical machine learning. Second-order methods are rarely used in practice due to their high computational cost, even they converge much faster than first-order methods. The state-of-the-art result for the second-order method to train an over-parameterized neural network can run in O(log(1/ϵ)) iterations and each iteration has O(mnd + n 3 ) running time, where n represent the number of data points, d is the dimension of the feature space of each data and m is the width of the neural network [Brand, Peng, Song and Weinstein ITCS 2021]. In this work, we further improve the convergence rate and the running time for each iteration to O(loglog(1/ϵ)) and O(mdτ 2 ) respectively, where m = Ω(n 4 ) and τ is the treewidth of the data matrix and usually very small. Our algorithm has a quadratic convergence rate, so it can be regarded as a truly second-order algorithm. To the best of our knowledge, our algorithm is the first to achieve a quadratic convergence rate for neural network training, with a per-iteration running time of O(mdτ 2 ).

关键词： Training Knowledge engineering Costs Neural networks Machine learning Big Data Computational efficiency Matrix decomposition Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Verify All Traffic: Towards Zero-Trust In-Network Intrusion Detection against Multipath Routing

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2155-2171页

作者： Zhao, Ziming Li, Zhaoxuan Xie, Xiaofei Liu, Zhipeng Li, Tingting Yu, Jiongchi Zhang, Fan Chen, Binbin School of Software Technology Zhejiang University Ningbo315100 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China ZJU-Hangzhou Global Scientific and Technological Innovation Center 311200 China Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province 310027 China Jiaxing Research Institute Zhejiang University 314000 China Zhengzhou Xinda Institute of Advanced Technology Zhengzhou450001 China Singapore State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security UCAS Beijing100049 China School of Computing and Information Systems Singapore Management University Singapore188065 Singapore Advanced Digital Sciences Center Singapore138632 Singapore Singapore University of Technology and Design SingaporeB96049 Singapore

With the popularity of encryption protocols, machine learning (ML)-based traffic analysis technologies have attracted widespread attention. To adapt to modern high-speed bandwidth, recent research is dedicated to advancing zero-trust intrusion detection by offloading feature extraction and model inference into the network dataplane. Especially, with the rise of programmable switches, achieving line-speed ML inference becomes promising. However, existing research only considers a single switch node as a relay to conduct evaluation. This is far from real-world deployments involving multiple switches (given that zero-trust security assumes that threats can originate from anywhere, including within the network), particularly the multi-path routing phenomenon that exists in practice. In this paper, we reveal practical challenges in the context of enabling line-speed model inference in the network dataplane. Furthermore, we propose FCPlane, the forwarding and computing integrated dataplane for zero-trust intrusion detection that aims to enable efficient load balancing while providing reliable traffic analysis results, even against multipath routing. The core idea is to reconcile forwarding and computation to the flowlet level, for which a tailor-made Markov chain model is designed. Based on two public traffic datasets, we evaluate seven state-of-the-art in-network traffic analysis models deployed in four types of topologies (three with multipath routing and one without) to explore performance impact and demonstrate the effectiveness of our proposal. © 1983-2012 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

R2DET: EXPLORING RELAXED ROTATION EQUIVARIANCE IN 2D OBJECT DETECTION

arXiv

引用

arXiv 2024年

作者： Wu, Zhiqiang Liu, Yingjie Dong, Hanlin Tang, Xuan Yang, Jian Jin, Bo Chen, Mingsong Wei, Xian Software Engineering Institute East China Normal University China School of Communication and Electronic Engineering East China Normal University China School of Geospatial Information Information Engineering University China School of Computer Science and Technology Tongji University China

Group Equivariant Convolution (GConv) empowers models to explore underlying symmetry in data, improving performance. However, real-world scenarios often deviate from ideal symmetric systems caused by physical permutation, characterized by non-trivial actions of a symmetry group, resulting in asymmetries that affect the outputs, a phenomenon known as Symmetry Breaking. Traditional GConv-based methods are constrained by rigid operational rules within group space, assuming data remains strictly symmetry after limited group transformations. This limitation makes it difficult to adapt to Symmetry-Breaking and nonrigid transformations. Motivated by this, we mainly focus on a common scenario: Rotational Symmetry-Breaking. By relaxing strict group transformations within Strict Rotation-Equivariant group Cn, we redefine a Relaxed Rotation-Equivariant group Rn and introduce a novel Relaxed Rotation-Equivariant GConv (R2GConv) with only a minimal increase of 4n parameters compared to GConv. Based on R2GConv, we propose a Relaxed Rotation-Equivariant Network (R2Net) as the backbone and develop a Relaxed Rotation-Equivariant Object Detector (R2Det) for 2D object detection. Experimental results demonstrate the effectiveness of the proposed R2GConv in natural image classification, and R2Det achieves excellent performance in 2D object detection with improved generalization capabilities and robustness. The code is available in https://***/wuer5/r2det. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Wavelet-based Global-Local Interaction Network with Cross-Attention for Multi-View Diabetic Retinopathy Detection

arXiv

引用

arXiv 2025年

作者： Hu, Yongting Lin, Yuxin Liu, Chengliang Luo, Xiaoling Dou, Xiaoyan Xu, Qihao Xu, Yong School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Ophthalmology Department Shenzhen Second People’s Hospital Shenzhen China

Multi-view diabetic retinopathy (DR) detection has recently emerged as a promising method to address the issue of incomplete lesions faced by single-view DR. However, it is still challenging due to the variable sizes and scattered locations of lesions. Furthermore, existing multi-view DR methods typically merge multiple views without considering the correlations and redundancies of lesion information across them. Therefore, we propose a novel method to overcome the challenges of difficult lesion information learning and inadequate multi-view fusion. Specifically, we introduce a two-branch network to obtain both local lesion features and their global dependencies. The high-frequency component of the wavelet transform is used to exploit lesion edge information, which is then enhanced by global semantic to facilitate difficult lesion learning. Additionally, we present a cross-view fusion module to improve multi-view fusion and reduce redundancy. Experimental results on large public datasets demonstrate the effectiveness of our method. The code is open sourced on https://***/HuYongting/WGLIN. Copyright © 2025, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Categorical Data Clustering via Value Order Estimated Distance Metric Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yiqun Zhao, Mingjie Jia, Hong Lu, Yang Li, Mengke Cheung, Yiu-Ming School of Computer Science and Technology Guangdong University of Technology Guangzhou China College of Electronics and Information Engineering Shenzhen University Shenzhen China Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China School of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong

Categorical data composed of qualitative valued attributes are ubiquitous in machine learning tasks. Due to the lack of well-defined metric space, categorical data distributions are difficult to be intuitively understood. Clustering is a popular data analysis technique suitable for data distribution understanding. However, the success of clustering often relies on reasonable distance metrics, which happens to be what categorical data naturally lack. This paper therefore introduces a new finding that the order relation among attribute values is the decisive factor in clustering accuracy, and is also the key to understanding categorical data clusters, because the essence of clustering is to order the clusters in terms of their admission to samples. To obtain the orders, we propose a new learning paradigm that allows joint learning of clusters and the orders. It alternatively partitions the data into clusters based on the distance metric built upon the orders and estimates the most likely orders according to the clusters. The algorithm achieves superior clustering accuracy with a convergence guarantee, and the learned orders facilitate the understanding of the non-intuitive cluster distribution of categorical data. Extensive experiments with ablation studies, statistical evidence, and case studies have validated the new insight into the importance of value order and the method proposition. The source code is temporarily opened in https://***/r/OCL-demo. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Reliable Central Nervous System Tumor Differentiation on MRI Images with Deep Neural Networks and Conformal Prediction 1

Reliable Central Nervous System Tumor Differentiation on MRI...

引用

1st Workshop on Explainable Artificial Intelligence for the Medical Domain, EXPLIMED 2024

作者： Balderas, Luis de Castro, María Moreno Lastra, Miguel Martínez, Jose P. Pérez, Francisco J. Laínez, Antonio Arauzo-Azofra, Antonio Benítez, José M. School of Sciences Technology and Engineering’s Doctorates Department of Computer Science and Artificial Intelligence DiCITS DaSCI iMUDS University of Granada Granada18071 Spain Department of Software Engineering DiCITS DaSCI iMUDS University of Granada Granada18071 Spain Radiodiagnosis Service Hospital Universitario "Virgen de las Nieves" Granada Spain ibs.Granada: Instituto Biosanitario de Granada Granada Spain Rural Engineering Department DiCITS Lab University of Córdoba Córdoba14005 Spain

Central nervous system tumors, particularly gliomas, rank among the top 10 causes of cancer-related deaths worldwide. Thus, precise differentiation of these tumors is crucial for effective treatment, which can reduce patient suffering and lower mortality rates. We propose a deep learning-based technique for glioma differentiation using MRI imaging, which incorporates two novel approaches. First, we represent perfusion sequences as time series, which serve as inputs for a Deep Neural Network (DNN) classifier. This classifier is trained to distinguish the sequences between low-grade glioma (LGG) and high-grade glioma (HGG). Second, we employ Conformal Prediction to calibrate the results, ensuring they include the true category with a 90% probability. This approach has been rigorously tested to evaluate its performance. Our experimental results demonstrate that our deep neural network not only provides accurate but also ensures trustworthy predictions. © 2024 Copyright © for this paper by its authors.

关键词： Lung cancer

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：