检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lin, Kun-Yu Ding, Henghui Zhou, Jiaming Tang, Yu-Ming Peng, Yi-Xing Zhao, Zhilin Loy, Chen Change Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China S-Lab Nanyang Technological University Singapore Institute of Big Data Fudan University China AI Thrust Hong Kong University of Science and Technology Guangzhou China Data Science Lab School of Computing & DataX Research Centre Macquarie University Australia

Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining), recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to efficient and effective video learners for open-vocabulary action recognition. Inspired by that humans perform actions in diverse environments, our work delves into an intriguing question: Can CLIP-based video learners effectively generalize to video domains they have not encountered during training? To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a comprehensive evaluation of five state-of-the-art CLIP-based video learners under various types of domain gaps. The evaluation demonstrates that previous methods exhibit limited action recognition performance in unseen video domains, revealing potential challenges of the cross-domain open-vocabulary action recognition task. In this paper, we focus on one critical challenge of the task, namely scene bias, and accordingly contribute a novel scene-aware video-text alignment method. Our key idea is to distinguish video representations apart from scene-encoded text representations, aiming to learn scene-agnostic video representations for recognizing actions across domains. Extensive experiments demonstrate the effectiveness of our method. The benchmark and code will be available at https://***/KunyuLin/XOV-Action/. Copyright © 2024, The Authors. All rights reserved.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Out-of-distribution detection learning with unreliable out-of-distribution sources 23

Out-of-distribution detection learning with unreliable out-o...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Haotian Zheng Qizhou Wang Zhen Fang Xiaobo Xia Feng Liu Tongliang Liu Bo Han Department of Computer Science Hong Kong Baptist University and School of Electronic Engineering Xidian University Department of Computer Science Hong Kong Baptist University Australian Artificial Intelligence Institute University of Technology Sydney Sydney AI Centre The University of Sydney School of Computing and Information Systems The University of Melbourne

Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open-world classification. However, it is typically hard to collect real out-of-distribution (OOD) data for training a predictor capable of discerning ID and OOD patterns. This obstacle gives rise to data generation-based learning methods, synthesizing OOD data via data generators for predictor training without requiring any real OOD data. Related methods typically pre-train a generator on ID data and adopt various selection procedures to find those data likely to be the OOD cases. However, generated data may still coincide with ID semantics, i.e., mistaken OOD generation remains, confusing the predictor between ID and OOD data. To this end, we suggest that generated data (with mistaken OOD generation) can be used to devise an auxiliary OOD detection task to facilitate real OOD detection. Specifically, we can ensure that learning from such an auxiliary task is beneficial if the ID and the OOD parts have disjoint supports, with the help of a well-designed training procedure for the predictor. Accordingly, we propose a powerful data generation-based learning method named Auxiliary Task-based OOD Learning (ATOL) that can relieve the mistaken OOD generation. We conduct extensive experiments under various OOD detection setups, demonstrating the effectiveness of our method against its advanced counterparts. The code is publicly available at: https://***/tmlr-group/ATOL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Diabetic Retinopathy by Transfer Learning Based Retinal Images

Identification of Diabetic Retinopathy by Transfer Learning ...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Sreenivas Reddy Sagili Chandrashekhar Goswami V.C. Bharathi S. Ananthi K Rani R. Sathya Department of computer science Rochester Institute Of Technology Rochester New York Department of Computer Science & Engineering MIT School of Computing MIT Art Design and Technology University Pune Maharashtra School of Computer Science and Engineering VIT-AP University Amaravati Andhra Pradesh India Advanced Research Centre for Future Networks and Digital Twin Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Information Technology M. Kumarasamy College of Engineering Karur Tamilnadu India Department of IT Kongunadu College of Engineering and Technology Trichy Tamil Nadu India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

The human eye is frequently considered to deliver a space into a person's strength because it is only with diabetic retinopathy (DR), a devastating eye illness caused by diabetes mellitus, that one may understand the subject's unprotected surface without invasive operations. There are certain disorders, notably vascular illness, that authority telltale indicators in the eye retina. Microaneurysms (MAs) are primary indicators of diabetic retinopathy (DR), making their detection crucial for an effective screening program that adheres to clinical procedures. Retinal examinations can reveal pathological deviations caused by limited ocular diseases such as arteriosclerosis, diabetes, cardiovascular disease hypertension and stroke. The proposed work introduces image processing algorithms, such as shady object identification, to predict the disorder or improve the contribution frame, thereby improving the perceptibility of vessels in color fundus frames. Following this enhancement, an automated classification algorithm, specifically a Convolutional Neural Network (CNN), is executed. The CNN architecture is designed to efficiently extract features from retinal frames, capturing complex patterns connected with diabetic retinopathy. The trained CNN is then assessed on a separate test condition, with its performance system of measurement-accuracy, specificity, recall, and Fl measure-being reported.

关键词： Diabetic retinopathy Pathology Image color analysis Transfer learning Retina Feature extraction Prediction algorithms Classification algorithms Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

Optimized Ensemble Algorithm for Predicting Metamaterial Antenna Parameters

引用

computers, Materials & Continua 2022年第6期71卷 4989-5003页

作者： El-Sayed M.El-kenawy Abdelhameed Ibrahim Seyedali Mirjalili Yu-Dong Zhang Shaima Elnazer Rokaia M.Zaki Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Centre for Artificial Intelligence Research and Optimization Torrens University AustraliaFortitude ValleyQLD 4006Australia Yonsei Frontier Lab Yonsei UniversitySeoul03722Korea School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Nile Higher Institute for Engineering and Technology MansouraEgypt Computer and Information Technology College Taif UniversityTaifSaudi Arabia Higher Institute of Engineering and Technology Kafrelsheikh Department of Electrical Engineering Shoubra Faculty of EngineeringBenha UniversityEgypt

Metamaterial Antenna is a subclass of antennas that makes use of metamaterial to improve *** antennas can overcome the bandwidth constraint associated with tiny *** learning is receiving a lot of interest in optimizing solutions in a variety of *** learning methods are already a significant component of ongoing research and are anticipated to play a critical role in today’s *** accuracy of the forecast is mostly determined by the model *** purpose of this article is to provide an optimal ensemble model for predicting the bandwidth and gain of the Metamaterial *** Vector Machines(SVM),Random Forest,K-Neighbors Regressor,and Decision Tree Regressor were utilized as the basic *** Adaptive Dynamic Polar Rose Guided Whale Optimization method,named AD-PRS-Guided WOA,was used to pick the optimal features from the *** suggested model is compared to models based on five variables and to the average ensemble *** findings indicate that the presented model using Random Forest results in a Root Mean Squared Error(RMSE)of(0.0102)for bandwidth and RMSE of(0.0891)for *** is superior to other models and can accurately predict antenna bandwidth and gain.

关键词： Metamaterial antenna machine learning ensemble model feature selection guided whale optimization support vector machines

来源：评论

学校读者我要写书评

暂无评论

A REFERENCE-FREE METRIC FOR LANGUAGE-QUERIED AUDIO SOURCE SEPARATION USING CONTRASTIVE LANGUAGE-AUDIO PRETRAINING

arXiv

引用

arXiv 2024年

作者： Xiao, Feiyang Guan, Jian Zhu, Qiaoxi Liu, Xubo Wang, Wenbo Qi, Shuhan Zhang, Kejia Sun, Jianyuan Wang, Wenwu College of Computer Science and Technology Harbin Engineering University Harbin China University of Technology Sydney Ultimo Australia Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Faculty of Computing Harbin Institute of Technology Harbin China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science University of Sheffield Sheffield United Kingdom

Language-queried audio source separation (LASS) aims to separate an audio source guided by a text query, with the signal-to-distortion ratio (SDR)-based metrics being commonly used to objectively measure the quality of the separated audio. However, the SDR-based metrics require a reference signal, which is often difficult to obtain in real-world scenarios. In addition, with the SDR-based metrics, the content information of the text query is not considered effectively in LASS. This paper introduces a reference-free evaluation metric using a contrastive language-audio pretraining (CLAP) module, termed CLAPScore, which measures the semantic similarity between the separated audio and the text query. Unlike SDR, the proposed CLAPScore metric evaluates the quality of the separated audio based on the content information of the text query, without needing a reference signal. Experiments show that the CLAPScore provides an effective evaluation of the semantic relevance of the separated audio to the text query, as compared to the SDR metric, offering an alternative for the performance evaluation of LASS systems. The code for evaluation is publicly available1 Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning

Is Complexity Required for Neural Network Pruning? A Case St...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Manas Gupta Efe Camci Vishandi Rudy Keneta Abhishek Vaidyanathan Ritwik Kanodia Ashish James Chuan-Sheng Foo Min Wu Jie Lin Institute for Infocomm Research (I2R) Agency for Science Technology and Research (A*STAR) Singapore School of Computing (SoC) National University of Singapore (NUS) Singapore School of Computer Science and Engineering (SCSE) Nanyang Technological University (NTU) Singapore Centre for Frontier AI Research (CFAR) Agency for Science Technology and Research (A*STAR) Singapore

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Pruning neural networks has become popular in the last decade when it was shown that a large number of weights can be safely removed from modern neural networks without compromising accuracy. Numerous pruning methods have been proposed since, each claiming to be better than prior art, however, at the cost of increasingly complex pruning methodologies. These methodologies include utilizing importance scores, getting feedback through back-propagation or having heuristics-based pruning rules amongst others. In this work, we question whether this pattern of introducing complexity is really necessary to achieve better pruning results. We benchmark these SOTA techniques against a simple pruning baseline, namely, Global Magnitude Pruning (Global MP), that ranks weights in order of their magnitudes and prunes the smallest ones. Surprisingly, we find that vanilla Global MP performs very well against the SOTA techniques. When considering sparsity-accuracy trade-off, Global MP performs better than all SOTA techniques at all sparsity ratios. When considering FLOPs-accuracy trade-off, some SOTA techniques outperform Global MP at lower sparsity ratios, however, Global MP starts performing well at high sparsity ratios and performs very well at extremely high sparsity ratios. Moreover, we find that a common issue that many pruning algorithms run into at high sparsity rates, namely, layer-collapse, can be easily fixed in Global MP. We explore why layer collapse occurs in networks and how it can be mitigated in Global MP by utilizing a technique called Minimum Threshold. We showcase the above findings on various models (WRN-28-8, ResNet-32, ResNet-50, MobileNet-V1 and FastGRNN) and multiple datasets (CIFAR-10, ImageNet and HAR-2).

关键词： Costs Art Accuracy Computational modeling Artificial neural networks Benchmark testing Network architecture

来源：评论

学校读者我要写书评

暂无评论

The Effect of Comorbidity on the Survival Rates of COVID-19 Using Quantum Machine Learning 7th

The Effect of Comorbidity on the Survival Rates of COVID-19 ...

引用

7th International Conference on Data Management, Analytics and Innovation, ICDMAI 2023

作者： Shahapure, Arsheyee Banerjee, Anindita Deshmukh, Rehan Computer Science and Engineering Dr. Vishwanath Karad MIT-World Peace University Paud Road Pune411036 India Centre for Development of Advanced Computing Corporate Research and Development C-DAC Innovation Park Panchavati Pashan Pune411008 India School of Biosciences and Technology Dr. Vishwanath Karad MIT-World Peace University Paud Road Pune411036 India

ISBN: (纸本)9789819914135

We report the effect of comorbidity on the survival rates of COVID-19 using quantum machine learning. Recent understanding of the novel coronavirus aims to verify the target organ of the virus, which could lead shortly to significant advances in the diagnosis and treatment of infected patients. An overview of the impact of the SARS-CoV-2 virus based on many different parameters such as age, type of comorbidity, and gender has been studied. The data calculations are done manually by referring to parent articles and using machine learning and quantum machine learning algorithm. It is helpful to verify the target age group, gender at risk of infection, and survival rates of the person. The data used is classical data, and quantum algorithms were run on it. We found out that the accuracy has increased to the classical machine learning state vector machine results. We found that pulmonary diseases are the most harmful type of comorbidity when an individual gets infected with COVID-19. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Collaborative Application Security Testing for DevSecOps An Empirical Analysis of Challenges, Best Practices and Tool Support

arXiv

引用

arXiv 2022年

作者： Rajapakse, Roshan Namal Zahedi, Mansooreh Babar, Muhammad Ali Centre for Research on Engineering Software Technologies School of Computer Science The University of Adelaide Australia Cyber Security Cooperative Research Centre Australia School of Computing and Information Systems The University of Melbourne Australia

DevSecOps is a software development paradigm that places a high emphasis on the culture of collaboration between developers (Dev), security (Sec) and operations (Ops) teams to deliver secure software continuously and rapidly. Adopting this paradigm effectively, therefore, requires an understanding of the challenges, best practices and available solutions for collaboration among these functional teams. However, collaborative aspects related to these teams have received very little empirical attention in the DevSecOps literature. Hence, we present a study focusing on a key security activity, Application Security Testing (AST), in which practitioners face difficulties performing collaborative work in a DevSecOps environment. Our study made novel use of 48 systematically selected webinars, technical talks and panel discussions as a data source to qualitatively analyse practitioner discussions on the most recent trends and emerging solutions in this highly evolving field. We find that the lack of features that facilitate collaboration built into the AST tools themselves is a key tool-related challenge in DevSecOps. In addition, the lack of clarity related to role definitions, shared goals, and ownership also hinders Collaborative AST (CoAST). We also captured a range of best practices for collaboration (e.g., Shift-left security), emerging communication methods (e.g., ChatOps), and new team structures (e.g., hybrid teams) for CoAST. Finally, our study identified several requirements for new tool features and specific gap areas for future research to provide better support for CoAST in DevSecOps. © 2022, CC BY.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Robust Attacks Detection Model for Internet of Flying Things based on Generative Adversarial Network (GAN) and Adversarial Training

引用

IEEE Internet of Things Journal 2025年

作者： Gaber, Tarek Ali, Tarek Nicho, Mathew Torky, Mohamed Engineering and Environment University of Salford School of Science Manchester United Kingdom Suez Canal University Faculty of Computers and Informatics Ismailia Egypt Manchester Metropolitan University Department of Computing and Mathematics Manchester United Kingdom Rabdan Academy Research and Innovation Centre Abu Dhabi United Arab Emirates University of Queensland School of Electrical Engineering and Computer Science Australia Egyptian Russian University-Badr City Faculty of Artificial Intelligence Cairo Egypt

The Internet of Flying Things (IoFT) holds significant promise in fields like disaster management and surveillance. However, it is increasingly vulnerable to cyberattacks that can compromise the confidentiality, integrity, and availability (CIA) of sensitive data. Despite the growing interest in proposing Intrusion Detection Systems (IDSs) for IoFT networks, current literature faces key limitations, particularly the shortage of publicly available IoFT datasets with diverse attacks, and the fact that existing IDSs lack robustness against sophisticated adversarial machine learning attacks. This paper is the first study to address these limitations by proposing a more resilient and accurate IDS tailored for IoFT networks (RIDS-IoFT). We introduce a novel IDS that leverages Generative Adversarial Networks (GANs) to generate a hybrid dataset that combines real IoFT traffic data with GAN-generated adversarial attacks, addressing the dataset diversity issue. Additionally, we introduce an innovative adversarial training method to enhance the system’s defense against evolving threats, such as Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), and Carlini & Wagner (C&W) attacks. The proposed RIDS-IoFT was evaluated using four machine learning models, Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Logistic Regression (LR), on two datasets: ECU-IoFT and CICIDS2018. The IDS’s performance was assessed based on its ability to detect both traditional and adversarial attacks. The results show that the Random Forest model achieved the highest detection accuracy, up to 96.5%, demonstrating superior performance across both real and hybrid datasets. The proposed RIDS-IoFT not only enhances detection accuracy but also strengthens resilience against adversarial threats, making it suitable for resource-constrained IoFT environments. In conclusion, this study presents a comprehensive approach to securing IoFT networks by combining real and synthetic d

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Capabilities of Latent Diffusion Models for Classification of Lung Diseases in Chest X-Rays

Unveiling the Capabilities of Latent Diffusion Models for Cl...

引用

IEEE International Symposium on Biomedical Imaging

作者： Junzhi Ning Xiaodan Xing Sheng Zhang Xiao Ma Guang Yang Department of Computing School of Engineering Imperial College London London UK Bioengineering Department and Imperial-X Imperial College London London UK National Heart and Lung Institute Imperial College London London UK School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Cardiovascular Research Centre Royal Brompton Hospital London UK School of Biomedical Engineering & Imaging Sciences King's College London UK

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Diffusion models have demonstrated remarkable ability in synthesizing chest X-ray (CXR) images, particularly by generating high-quality samples to address the scarcity and imbalance of annotated CXR datasets. While these models excel in generating realistic samples-suggesting that they contain rich discriminative information effectively harnessing this capability for disease classification and decomposition remains a challenge. This study investigates an approach that leverages latent conditional diffusion models, which are conditioned on corresponding radiology reports, for lung disease classification in CXRs. Specifically, we employ a pre-trained latent conditional diffusion model for CXRs to predict noise estimates for a noisy input lung CXR under various disease conditions. By comparing the noise estimation errors associated with different class prompts, we determine the most probable disease classification based on the minimal error. Through the experiments, we demonstrate that the CXR diffusion-based classifier not only achieves zero-shot classification performance comparable to existing models but also reveals lesion regions aligning with ground truth lesion areas in CXRs.

关键词： Pulmonary diseases Lungs Noise Pipelines Radiology Diffusion models Lesions Noise measurement X-ray imaging Biomedical imaging

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：