检索结果-内蒙古大学图书馆

Search is All You Need for Few-shot Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Qishan Guo, Jia Gao, Shuyong Wang, Haofen Xiong, Li Hu, Junjie Guo, Hanqi Zhang, Wenqiang Academy for Engineering and Technology Fudan University Shanghai China School of Biomedical Engineering Tsinghua University Beijing China School of Computer Science Fudan university Shanghai China College of Design & Innovation Tongji University Shanghai China School of Physics and Mechanical & Electrical Engineering Hexi University Gansu China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan university Shanghai China

Few-shot anomaly detection (FSAD) has emerged as a crucial yet challenging task in industrial inspection, where normal distribution modeling must be accomplished with only a few normal images. While existing approaches typically employ multi-modal foundation models combining language and vision modalities for prompt-guided anomaly detection, these methods often demand sophisticated prompt engineering and extensive manual tuning. In this paper, we demonstrate that a straightforward nearest-neighbor search framework can surpass state-of-the-art performance in both single-class and multi-class FSAD scenarios. Our proposed method, VisionAD, consists of four simple yet essential components: (1) scalable vision foundation models that extract universal and discriminative features;(2) dual augmentation strategies - support augmentation to enhance feature matching adaptability and query augmentation to address the oversights of single-view prediction;(3) multi-layer feature integration that captures both low-frequency global context and high-frequency local details with minimal computational overhead;and (4) a class-aware visual memory bank enabling efficient one-for-all multi-class detection. Extensive evaluations across MVTec-AD, VisA, and Real-IAD benchmarks demonstrate VisionAD’s exceptional performance. Using only 1 normal images as support, our method achieves remarkable image-level AUROC scores of 97.4%, 94.8%, and 70.8% respectively, outperforming current state-of-the-art approaches by significant margins (+1.6%, +3.2%, and +1.4%). The training-free nature and superior few-shot capabilities of VisionAD make it particularly appealing for real-world applications where samples are scarce or expensive to obtain. Code is available at ***/Qiqigeww/VisionAD. Copyright © 2025, The Authors. All rights reserved.

关键词： Normal distribution

Towards Understanding the Security of Modern Image Captchas and Underground Captcha-Solving Services

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2019年第2期2卷 118-144页

作者： Haiqin Weng Binbin Zhao Shouling Ji Jianhai Chen Ting Wang Qinming He Raheem Beyah College of Computer Science and Technology Zhejiang University Department of Computer Science and Engineering Lehigh University School of Electrical and Computer Engineering Georgia Institute of Technology

Image captchas have recently become very popular and are widely deployed across the Internet to defend against abusive programs. However, the ever-advancing capabilities of computer vision have gradually diminished the security of image captchas and made them vulnerable to attack. In this paper, we first classify the currently popular image captchas into three categories: selection-based captchas, slide-based captchas, and click-based captchas. Second, we propose simple yet powerful attack frameworks against each of these categories of image captchas. Third, we systematically evaluate our attack frameworks against 10 popular real-world image captchas,including captchas from ***, ***, and ***. Fourth, we compare our attacks against nine online image recognition services and against human labors from eight underground captcha-solving services. Our evaluation results show that(1) each of the popular image captchas that we study is vulnerable to our attacks;(2) our attacks yield the highest captcha-breaking success rate compared with state-of-the-art methods in almost all scenarios; and(3) our attacks achieve almost as high a success rate as human labor while being much *** on our evaluation, we identify some design flaws in these popular schemes, along with some best practices and design principles for more secure captchas. We also examine the underground market for captcha-solving services, identifying 152 such services. We then seek to measure this underground market with data from these services. Our findings shed light on understanding the scale, impact, and commercial landscape of the underground market for captcha solving.

关键词： image captchas captcha security captcha-solving service underground market

Cooperative Urban Air Mobility Trajectory Design for Power and AoI Optimization: A Multi-agent Reinforcement Learning Approach

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Kim, Hyeonsu Aung, Pyae Sone Munir, Md. Shirajum Saad, Walid Hong, Choong Seon Kyung Hee University Department of Artificial Intelligence Gyeonggi-do Yongin-si17104 Korea Republic of Kyung Hee University Department of Computer Science and Engineering Gyeonggi-do Yongin-si17104 Korea Republic of University of West Georgia School of Computing Analytics and Modeling CarrolltonGA30118 United States Virginia Tech Bradley Department of Electrical and Computer Engineering VA24061 United States

Urban air mobility (UAM) is a revolutionary urban transportation paradigm that aims to transport passengers, emphasizing safety, power efficiency, and autonomous operation. Also, UAM aircraft needs to regularly transmit status and environmental conditions to the base stations (BS) to maintain updated information in the system. Hence, the age of information (AoI) can be used as a status measurement indicator to evaluate the degree to which the current status information of UAM aircraft is outdated. Optimizing each UAM aircraft's flight trajectory for both power efficiency and safety, while also minimizing the AoI for timely data transmission forms a computationally challenging NP-hard problem. In this paper, a multi-agent deep reinforcement learning based solution is proposed to address this problem by exploiting a sophisticated method to handle multidimensional decision spaces for power efficiency, safety in trajectory planning, and AoI. Simulation results demonstrate that our method produce a power efficiency improvement of 8.8% compared to the PPO method and 13.8% compare to the detour method. Furthermore, the proposed approach significantly improve the data freshness by up to 31.5%, 31.7%, and 12.9% in terms of AoI compared to the greedy, detour, and single PPO methods, respectively. © 1967-2012 IEEE.

关键词： Urban transportation

Advancing Visual Marketing Strategies Through Deep Learning-Based Image Recognition for Improved Customer Engagement and Brand Visibility

学校读者我要写书评

暂无评论

Advancing Visual Marketing Strategies Through Deep Learning-...

Automation and Computation (AUTOCOM), International Conference on

作者： Ramu Pandiri Nnadhini T J R. Velmurugan A. Menaga J. Karpagam Vinothkumar K Infomatics Corp Dallas Texas Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences-(SIMATS) Chennai India Karpagam Academy of Higher Education Coimbatore India Department of MBA St Joseph's College of Engineering Chennai India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore India Department of ECE PSNA College of Engineering and Technology Dindigul India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

This paper aims at analyzing the effectiveness of utilizing deep learning-based image recognition in enhancing the visual marketing thereby determining the extent to which clients' attention and brand awareness are likely to be affected. It uses convolutional neural networking (CNN) to analyze and classify the visual content and the models used include VGG16, ResNet50, InceptionV3. An effective implementation of the data gathering, feature engineering, and algorithm development can be seen in the enhancing of the marketing effectiveness. This entails better accuracy of images in classification. This involves gaining high engagement rates from the customers. probabilities of high visibility of the brands across the various platforms. The study points at the possibility of deep learning technologies in changing visual marketing practices and therefore serves as a useful reference guide to business entity that wish to align themselves with adequate marketing practices in the growing digital landscape.

关键词： Deep learning Visualization Technological innovation Image recognition Performance analysis Classification algorithms Convolutional neural networks Stress Residual neural networks Business

Complex media microstrip ridge structures: Formulation and basic characteristics of ferrite structures

学校读者我要写书评

暂无评论

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES 1996年第9期44卷 1563-1568页

作者： Hanson, GW IEEE Department of Electrical Engineering and Computer Science University of Wisconsin-Milwaukee

Microstrip transmission lines residing on bianisotropic material ridges embedded in a multilayered environment are studied using a coupled set of integral equations (IE's), The full-wave IE formulation accounts for general linear media in the ridge region using equivalent polarization currents residing in a multilayered bianisotropic background, Numerical results showing basic propagation characteristics are presented for a variety of single and coupled ferrite ridge structures, It is shown that the use of finite width ferrite ridges as either substrates or superstrates can produce nonreciprocity while confining the ferrite material to a small area in the vicinity of the transmission line.

关键词： .formulation ridge structures propagation characteristics Bianisotropic Complex Media Microstrip Microstrip transmission lines material ridges ridge region ferrite ridge

Diagnosis of rheumatic and autoimmune diseases dataset

学校读者我要写书评

暂无评论

Data in Brief 2025年 60卷

作者： Mohammed Fadhil Mahdi Arezoo Jahani Dhafar Hamed Abd Faculty of Electrical and Computer Engineering Sahand University of Technology Tabriz Iran College of Computer Science and Information Technology University of Anbar Ramadi Iraq

This study presents a primary dataset collected from one hospital and three laboratories in Iraq between 2019 and 2024. The dataset includes both the case and control groups, the case group comprising patients diagnosed with six common rheumatic and autoimmune diseases: rheumatoid arthritis, reactive arthritis, ankylosing spondylitis, Sjögren syndrome, systemic lupus erythematosus, and psoriatic arthritis. The dataset contains records of 12,085 patients with rheumatic and autoimmune diseases. Patient privacy is ensured through data anonymization. The dataset includes 14 features in seven classes, aiding the development of machine learning models for the early and accurate diagnosis of rheumatic and autoimmune diseases. This dataset is valuable for clinical decision support, remote healthcare, drug development, and medical diagnosis. It facilitates early diagnosis, supports explainable artificial intelligence models, advances precision medicine, enhances research, and reduces diagnostic costs and time.

关键词： Rheumatoid arthritis Reactive arthritis Ankylosing spondylitis Sjögren syndrome Systemic lupus erythematosus Psoriatic arthritis

Real-time raw signal genomic analysis using fully integrated memristor hardware

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Peiyi Wang, Shengbo Mao, Ruibin Siegel, Sebastian Pedretti, Giacomo Ignowski, Jim Strachan, John Paul Luo, Ruibang Li, Can Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Forschungszentrum Jülich GmbH Jülich Germany Hewlett Packard Labs Hewlett Packard Enterprise MilpitasCA United States RWTH Aachen University Aachen Germany Department of Computer Science School of Computing and Data Science The University of Hong Kong Hong Kong

Advances in third-generation sequencing have enabled portable and real-time genomic sequencing, but real-time data processing remains a bottleneck, hampering on-site genomic analysis due to prohibitive time and energy costs. These technologies generate a massive amount of noisy analog signals that traditionally require basecalling and digital mapping, both demanding frequent and costly data movement on von Neumann hardware. To overcome these challenges, we present a memristor-based hardware-software co-design that processes raw sequencer signals directly in analog memory, effectively combining the separated basecalling and read mapping steps. Here we demonstrate, for the first time, end-to-end memristor-based genomic analysis in a fully integrated memristor chip. By exploiting intrinsic device noise for locality-sensitive hashing and implementing parallel approximate searches in content-addressable memory, we experimentally showcase on-site applications including infectious disease detection and metagenomic classification. Our experimentally-validated analysis confirms the effectiveness of this approach on real-world tasks, achieving a state-of-the-art 97.15% F1 score in virus raw signal mapping, with 51× speed up and 477× energy saving compared to implementation on a state-of-the-art ASIC. These results demonstrate that memristor-based in-memory computing provides a viable solution for integration with portable sequencers, enabling truly real-time on-site genomic analysis for applications ranging from pathogen surveillance to microbial community profiling. © 2025, CC BY-NC-SA.

关键词： Analog storage

A 3D Continuous-Space Electromagnetic Channel Model for 6G Tri-Polarized Multi-user Communications

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Yue Wang, Cheng-Xiang Huang, Jie Thompson, John Vincent Poor, H. The National Mobile Communications Research Laboratory School of Information Science and Engineering Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211111 China The Institute for Digital Communications School of Engineering University of Edinburgh EdinburghEH9 3JL United Kingdom The Department of Electrical and Computer Engineering Princeton University PrincetonNJ United States

It is envisioned that the sixth generation (6G) and beyond 6G (B6G) wireless communication networks will enable global coverage in space, air, ground, and sea. In this case, both base stations and users can be mobile and will tend to move continuously in three-dimensional (3D) space. Therefore, obtaining channel state information (CSI) in 3D continuous-space is crucial for the design and performance evaluation of future 6G and B6G wireless systems. On the other hand, new 6G technologies such as integrated sensing and communications (ISAC) will also require prior knowledge of CSI in 3D continuous-space. In this paper, a 3D continuous-space electromagnetic channel model is proposed for tri-polarized multi-user communications, taking into account scatterers and spherical wavefronts. Scattered fields are calculated using the method of moments (MoM) with high accuracy. Spherical wave functions are utilized to decompose the dyadic Green's functions that connect the transmitted source currents and the received electric fields. Simulation results demonstrate that transmit power, apertures, scatterers, and sample intervals have significant impacts on statistical properties and channel capacities, providing insights into the performance of continuous-space electromagnetic channel models and the design of future wireless systems. © 2025, CC BY.

关键词： Spheres

Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6G

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Jiayi Liu, Ziheng Zhu, Yiyang Shi, Enyu Xu, Bokai Yuen, Chau Niyato, Dusit Debbah, Mérouane Jin, Shi Ai, Bo Shen, Xuemin School of Electronic and Information Engineering The Frontiers Science Center for Smart High-Speed Railway System Beijing jiaotong University Beijing100044 China School of Electrical and Electronics Engineering Nanyang Technological University 639798 Singapore College of Computing and Data Science Nanyang Technological University 639798 Singapore KU 6G Research Center Department of Computer and Information Engineering Khalifa University Abu Dhabi127788 United Arab Emirates CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

The introduction of intelligent interconnectivity between the physical and human worlds has attracted great attention for future sixth-generation (6G) networks, emphasizing massive capacity, ultra-low latency, and unparalleled reliability. Wireless distributed networks and multi-agent reinforcement learning (MARL), both of which have evolved from centralized paradigms, are two promising solutions for the great attention. Given their distinct capabilities, such as decentralization and collaborative mechanisms, integrating these two paradigms holds great promise for unleashing the full power of 6G, attracting significant research and development attention. This paper provides a comprehensive study on MARL-assisted wireless distributed networks for 6G. In particular, we introduce the basic mathematical background and evolution of wireless distributed networks and MARL, as well as demonstrate their interrelationships. Subsequently, we analyze different structures of wireless distributed networks from the perspectives of homogeneous and heterogeneous. Furthermore, we introduce the basic concepts of MARL and discuss two typical categories, including model-based and model-free. We then present critical challenges faced by MARL-assisted wireless distributed networks, providing important guidance and insights for actual implementation. We also explore an interplay between MARL-assisted wireless distributed networks and emerging techniques, such as information bottleneck and mirror learning, delivering in-depth analyses and application scenarios. Finally, we outline several compelling research directions for future MARL-assisted wireless distributed networks. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning