检索结果-内蒙古大学图书馆

Semi-Patchcore: A Novel Two-Staged Method for Semi-Supervised Anomaly detection and localization

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Xie, Shuo Wu, Xiaojun Yu Wang, Michael Harbin Inst Technol Shenzhen Sch Mech Engn & Automat Shenzhen 518055 Peoples R China Great Bay Univ Sch Adv Engn Dongguan 523000 Peoples R China

Product surface defect detection is a crucial technology in industrial production. The adoption of deep learning-based algorithms for inspecting product surface defects has been steadily increasing due to their superior detection capability and enhanced generalization performance. However, current deep learning-based algorithms primarily focus on supervised approaches, which can be inefficient and costly. In this article, we present a novel pipeline for semi-supervised defect detection called Semi-Patchcore, which achieves comparable defect detection performance to weakly supervised methods using only defect-free and unlabeled samples for training. Initially, we establish a memory bank using a labeled defect-free training dataset. Subsequently, we compare the unlabeled mixed data with the features in the memory bank to derive pseudo-class labels. Finally, we train a segmentation network based on DeepLabV3+ using the pseudo-classification labels. To evaluate the performance of our approach, we conduct comparative experiments on four public datasets: MVTecAD dataset, DAGM dataset, BTAD dataset, and KSDD2 dataset. The experimental results demonstrate that our method outperforms state-of-the-art semi-supervised or unsupervised methods in terms of superiority and generalization. Additionally, we explore the impact of label issues on supervised learning observed in this study. Our method also surpasses some weakly supervised segmentation algorithms, showcasing its effectiveness in industrial defect detection.

关键词： Feature extraction Defect detection Anomaly detection Training Image reconstruction Location awareness Generative adversarial networks Costs Classification algorithms Semantic segmentation detection and localization memory bank Semi-Patchcore semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Rethinking Image Forgery detection and localization via Regression Perspective

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2025年

作者： Zhang, Li Li, Dong Zhong, Yan Zhu, Jiaying Wang, Rujing Wu, Xingyu Wang, Xue Liu, Liu Hefei Univ Technol Hefei 230026 Peoples R China Univ Sci & Technol China Hefei 230026 Peoples R China Chinese Acad Sci Inst Intelligent Machines Hefei 230031 Peoples R China Chinese Acad Sci Hefei Inst Phys Sci Hefei 230031 Peoples R China Peking Univ Beijing 100000 Peoples R China Hong Kong Polytech Univ PolyU Dept Data Sci & Artificial Intelligence Hong Kong Peoples R China

Image Forgery detection and localization is rapidly advancing in the field of computer vision. Most methods locate forged regions in the form of segmentation and subsequently perform detection, facing challenges such as false detections (i.e., FPs) and inaccurate boundaries. In this work, we suggest rethinking the Image Forgery detection and localization (IFDL) task from a regression perspective and propose the CatmullRom Splines-based Regression Network (CSR-Net) to address these issues. Specifically, we first design an adaptive CutmullRom splines fitting scheme to predict coarse forged regions. Subsequently, we develop a novel rescoring mechanism that filters out samples with no response in both the classification and instance branches to reduce false positives. Besides, a learnable texture extraction module decouples horizontal and vertical forgery features, extracting more robust contour representations to further refine boundaries and suppress false detections. Compared to segmentation-based methods our method is simple but effective due to the unnecessity of post-processing. Extensive experiments conducted on several challenging benchmarks demonstrate that our method outperforms state-of-the-art methods qualitatively and quantitatively. Particularly, CSR-Net achieves optimal performance on three real-world datasets, indicating the applicability of our method to real scenarios such as social media and multi-tampered regions.

关键词： Splines (mathematics) Forgery Location awareness Electronic mail Image segmentation Accuracy Shape Process control Interpolation Feature extraction Image forgery detection and localization catmullrom splines regression methods

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Progressive Image Forgery detection and localization Method Based on UNet

引用

BIG DATA AND COGNITIVE COMPUTING 2024年第9期8卷 119页

作者： Liu, Yang Li, Xiaofei Zhang, Jun Li, Shuohao Hu, Shengze Lei, Jun Natl Univ Def Technol Lab Big Data & Decis Changsha 410000 Peoples R China

The rapid development of generative technologies has made the production of forged products easier, and AI-generated forged images are increasingly difficult to accurately detect, posing serious privacy risks and cognitive obstacles to individuals and society. Therefore, constructing an effective method that can accurately detect and locate forged regions has become an important task. This paper proposes a hierarchical and progressive forged image detection and localization method called HPUNet. This method assigns more reasonable hierarchical multi-level labels to the dataset as supervisory information at different levels, following cognitive laws. Secondly, multiple types of features are extracted from AI-generated images for detection and localization, and the detection and localization results are combined to enhance the task-relevant features. Subsequently, HPUNet expands the obtained image features into four different resolutions and performs detection and localization at different levels in a coarse-to-fine cognitive order. To address the limited feature field of view caused by inconsistent forgery sizes, we employ three sets of densely cross-connected hierarchical networks for sufficient interaction between feature images at different resolutions. Finally, a UNet network with a soft-threshold-constrained feature enhancement module is used to achieve detection and localization at different scales, and the reliance on a progressive mechanism establishes relationships between different branches. We use ACC and F1 as evaluation metrics, and extensive experiments on our method and the baseline methods demonstrate the effectiveness of our approach.

关键词： computer vision fake images detection and localization hierarchical network UNet

来源：评论

学校读者我要写书评

暂无评论

Joint detection and localization in Distributed MIMO Radars Employing Waveforms With Imperfect Auto- and Cross-Correlation

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2023年第12期72卷 16524-16537页

作者： Lai, Yangming Venturino, Luca Grossi, Emanuele Yi, Wei Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China Univ Cassino & Southern Lazio Dept Elect & Informat Engn DIEI I-03043 Cassino Italy Consorzio Nazl Interuniv Telecomunicazioni I-43124 Parma Italy

This article deals with the problem of joint detection and localization of multiple targets in a distributed multiple-input multiple-output radar system where the emitted waveforms present imperfect auto- and cross-correlation functions. In this context, the sidelobe masking effects can considerably degrade the detection and localization performance of correlation-based detectors. To address this issue, we first derive a convenient discrete-time signal model, wherein the echoes generated by a target towards each receive antenna are regarded as a subspace signal. Then, we formulate the joint detection and localization problem as a composite multiple hypothesis test and derive the optimal solution according to a generalized information criterion, whose complexity scales exponentially with the number of prospective targets. To reduce the computational burden, we derive two iterative approximate solutions which detect and localize one target at a time from the noisy data, upon mitigating the sidelobe masking caused by the previously-detected ones. Finally, we provide an extensive numerical analysis to demonstrate the effectiveness of the proposed solutions, even in the challenging case where an unknown number of strong and weak targets is present in the covered area.

关键词： Distributed MIMO radar detection and localization generalized information criterion generalized likelihood ratio test subspace detection sidelobe masking

来源：评论

学校读者我要写书评

暂无评论

detection and localization of biased load attacks in smart grids via interval observer

引用

INFORMATION SCIENCES 2021年 552卷 291-309页

作者： Wang, Xinyu Luo, Xiaoyuan Zhang, Mingyue Jiang, Zhongping Guan, Xinping Yanshan Univ Sch Elect Engn Qinhuangdao 066004 Hebei Peoples R China NYU Tandon Sch Engn Brooklyn NY 11201 USA Shanghai Jiao Tong Univ Sch Elect & Elect Engn Shanghai 200240 Peoples R China

The biased load attacks pose enormous security risks to smart grids, due to the characteristics of spoofing attack. To handle the risks, a novel scheme for detecting and localizing biased load attacks is developed. Firstly, an unknown input interval observer is designed to mitigate the influences of disturbances and regional interconnection information, contributing to an accurate estimation of the interval state. Secondly, considering the feature of interval residuals, a novel detection criterion is developed to eliminate the limitation resulted by the prior threshold in the existing detection techniques. In addition, a logic judgment matrix is established based on the combination of sensor set, addressing the problem of attack detection and localization under structural vulnerability. Finally, the simulation results indicate that the developed scheme can detect and localize the biased load attacks effectively. Also, the developed scheme shows superior performance than state-of-the-art techniques. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Biased load attack Security Interval observer detection and localization

来源：评论

学校读者我要写书评

暂无评论

detection and localization of cyber attacks on water treatment systems:an entropy-based approach

引用

Frontiers of Information Technology & Electronic Engineering 2022年第4期23卷 587-603页

作者： Ke LIU Mufeng WANG Rongkuan MA Zhenyong ZHANG Qiang WEI State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001China College of Control Science and Engineering Zhejiang UniversityHangzhou310027China

With the advent of Industry 4.0,water treatment systems(WTSs)are recognized as typical industrial cyber-physical systems(iCPSs)that are connected to the open *** information technology(IT)benefits the WTS in the aspects of reliability,efficiency,and ***,the vulnerabilities exposed in the communication and control infrastructure on the cyber side make WTSs prone to cyber *** traditional IT system oriented defense mechanisms cannot be directly applied in safety-critical WTSs because the availability and real-time requirements are of great *** this paper,we propose an entropy-based intrusion detection(EBID)method to thwart cyber attacks against widely used controllers(e.g.,programmable logic controllers)in WTSs to address this *** of the varied WTS operating conditions,there is a high false-positive rate with a static threshold for ***,we propose a dynamic threshold adjustment mechanism to improve the performance of *** validate the performance of the proposed approaches,we built a high-fidelity WTS testbed with more than 50 measurement *** conducted experiments under two attack scenarios with a total of 36attacks,showing that the proposed methods achieved a detection rate of 97.22%and a false alarm rate of 1.67%.

关键词： Industrial cyber-physical system Water treatment system Intrusion detection Abnormal state detection and localization Information theory

来源：评论

学校读者我要写书评

暂无评论

Novel cyber-physical collaborative detection and localization method against dynamic load altering attacks in smart energy grids

引用

Global Energy Interconnection 2024年第3期7卷 362-376页

作者： Xinyu Wang Xiangjie Wang Xiaoyuan Luo Xinping Guan Shuzheng Wang School of Electrical Engineering Yanshan UniversityQinhuangdao066004P.R.China School of Electrical Engineering Jiangsu Collaborative Innovation Center for Smart Distribution NetworkNanjing636600P.R.China School of Electronic and Electrical Engineering Shanghai Jiaotong UniversityShanghai200240P.R.China

Owing to the integration of energy digitization and artificial intelligence technology,smart energy grids can realize the stable,efficient and clean operation of power ***,the emergence of cyber-physical attacks,such as dynamic load-altering attacks(DLAAs)has introduced great challenges to the security of smart energy ***,this study developed a novel cyber-physical collaborative security framework for DLAAs in smart energy *** proposed framework integrates attack prediction in the cyber layer with the detection and localization of attacks in the physical ***,a data-driven method was proposed to predict the DLAA sequence in the cyber *** designing a double radial basis function network,the influence of disturbances on attack prediction can be *** on the prediction results,an unknown input observer-based detection and localization method was further developed for the physical *** addition,an adaptive threshold was designed to replace the traditional precomputed threshold and improve the detection performance of the ***,through the collaborative work of the cyber-physics layer,injected DLAAs were effectively detected and *** with existing methodologies,the simulation results on IEEE 14-bus and 118-bus power systems verified the superiority of the proposed cyber-physical collaborative detection and localization against DLAAs.

关键词： Smart energy grids Cyber-physical system Dynamic load altering attacks Attack prediction detection and localization

来源：评论

学校读者我要写书评

暂无评论

Subspace-Based detection and localization in Distributed MIMO Radars 12

Subspace-Based Detection and Localization in Distributed MIM...

引用

IEEE 12th Sensor Array and Multichannel Signal Processing Workshop (SAM)

作者： Lai, Yangming Venturino, Luca Grossi, Emanuele Yi, Wei Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Peoples R China Univ Cassino & Southern Lazio Dept Elect & Informat Engn Cassino Italy Natl Interunivs Consortium Telecommun Parma Italy

ISBN: (纸本)9781665406338

In this paper, we consider a distributed multipleinput multiple-output (MIMO) radar which radiates waveforms with non-ideal cross- and auto-correlation functions and derive a novel subspace-based procedure to detect and localize multiple prospective targets. The proposed solution solves a sequence of composite binary hypothesis testing problems by resorting to the generalized information criterion (GIC);in particular, at each step, it aims to detect and localize one additional target, upon removing the interference caused by the previously-detected targets. An illustrative example is provided.

关键词： detection and localization distributed MIMO radar generalized information criterion non-ideal correlation.

来源：评论

学校读者我要写书评

暂无评论

A Scheme of Polarimetric Superresolution for Multitarget detection and localization

引用

IEEE SIGNAL PROCESSING LETTERS 2021年 28卷 439-443页

作者： Wang, Shengbin Luo Xu, Zhenhai Dong, Wei Wang, Guoyu Natl Univ Def Technol State Key Lab Complex Electromagnet Environm Effe Changsha 410000 Peoples R China

In the conventional superresolution, multiple targets are usually separated based on the differences in their locations or Doppler frequencies. The polarization scattering matrix (PSM), as a unique "label" of a target, is very beneficial to radar superresolution, but it is usually neglected. In this paper, a novel scheme of polarimetric superresolution (PSR) is proposed for multitarget detection and localization. We divide the transmit pulse into four parts and modulate the polarization states of each subpulse to derive the sampling in the polarization domain. In the framework of Bayesian compressive sensing (BCS), the estimations of target parameters, including the range, angle and PSM, are derived. However, the off-grid problem results in a number of false targets. To eliminate the false targets, we specially design a true target extractor based on the estimated PSM of each target. With the PSR scheme, each target can be successfully detected and precisely localized in a single pulse. Simulation results demonstrate the effectiveness of the proposed scheme.

关键词： Superresolution Estimation Radar Array signal processing Signal to noise ratio Parametric statistics Indexes Bayesian compressive sensing detection and localization polarimetric superresolution polarization scattering matrix true target extractor

来源：评论

学校读者我要写书评

暂无评论

Failure detection and localization for timed event graphs in (max, plus )-algebra

引用

DISCRETE EVENT DYNAMIC SYSTEMS-THEORY AND APPLICATIONS 2021年第4期31卷 513-552页

作者： Le Corronc, Euriell Pencole, Yannick Sahuguede, Alexandre Paya, Claire Univ Toulouse CNRS LAAS UPS Toulouse France

In this paper, we address the problem of failure detection and localization in a Timed Discrete Event System (TDES) such (max,+)-linear system graphically modeled by a Timed Event Graph (TEG). The considered failures are changes on holding times or tokens of the TEG places that can provoke shifts between an observed outcoming timed flow and an expected outcoming timed flow (for a given incoming timed flow). Indicators are built to first detect such shifts relying on the (max,+) algebraic framework and the residuation theory. An analysis of the indicators' values provides information about time or event failure that could have happen. Then, thanks to the knowledge of the behavior of the system through its corresponding TEG, sets of failures that could explain the detected shifts are obtained. It comes from matrices of signatures for each indicator built on each observable output of the system. An example of application is proposed to experiment exhaustively failures of type time and event on each place of the TEG.

关键词： Failure diagnosis detection and localization Timed event graphs (max, plus )-linear systems Dioid and residuation theory Toolbox

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：