检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Enze Ji Shi Chen Tiandong Ji Jing Li Zhikui Chen Computer Network Information Center Chinese Academy of Sciences Beijing China Big Data Institute Hong Kong University of Science and Technology Hong Kong China School of Software Technology Dalian University of Technology Dalian China State Grid Liaoning Marketing Service Center Shenyang China

Few-shot classification has gained significant attention owing to the effectiveness in classifying unseen classes with a few annotated images. Although previous works achieve encouraging classification performance, they heavily rely on one-hot labels during the meta-learning process, which may result in the supervision collapse and limited generalization. To address these challenges, the few-shot classification based on a self-supervised multi-task distillation (SMD) is proposed for mitigating the nuisance arising from one-hot labels. Specifically, SMD formulates multiple auxiliary tasks to enhance the cross entropy classification in a multi-task learning manner, including the self-supervised classification task and the self-distilled classification task. These auxiliary tasks do not rely on one-hot labels in meta-learning, which can effectively enhance generalization performance of the model. Finally, extensive experiment results on two benchmark datasets, i.e., CIFAR-FS and FC-100, demonstrate the superiority and effectiveness of SMD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Look at Service Meshes 12

A Look at Service Meshes

引用

12th International Conference on Information, Intelligence, Systems and Applications, IISA 2021

作者： Koschel, Arne Bertram, Marvin Bischof, Richard Schulze, Kevin Schaaf, Marc Astrova, Irina University of Applied Sciences and Arts Hannover Faculty Iv Department of Computer Science Hannover Germany University of Applied Sciences Northwestern Switzerland Institute of Information Systems Olten Switzerland Tallinn University of Technology School of It Department of Software Science Tallinn Estonia

ISBN: (纸本)9781665400329

Service meshes can be seen as an infrastructure layer for microservice-based applications that are specifically suited for distributed application architectures. It is the goal to introduce the concept of service meshes and its use for microservices with the example of an open source service mesh called Istio. This paper gives an introduction into the service mesh concept and its relation to microservices. It also gives an overview of selected features provided by Istio as relevant to the above concept and provides a small sample setup that demonstrates the core features. © 2021 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Detection of Backdoor Attacks Using Targeted Universal Adversarial Perturbations for Deep Neural Networks

SSRN

引用

SSRN 2023年

作者： Qu, Yubin Huang, Song Chen, Xiang Wang, Xingya College of Command and Control Engineering Army Engineering University of PLA Nanjing210007 China School of Information Engineering Jiangsu College of Engineering and Technology Nantong226001 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China School of Information Science and Technology Nantong University Nantong226019 China College of Computer Science and Technology Nanjing Tech University China

The backdoors using targeted universal adversarial perturbations against deep neurall networks has been explored. This backdoor does not require data poisoning or model tampering. Rretraining deep neural network models using adversarial training for security is time-consuming and does not apply to deep neural networks in runtime. We want to detect backdoors using a black-box testing approach. We observe that after superimposing random noise on the input of a backdoor attack, the output still tends to remain the same, so we propose Sequential Analysis method based on the Metamorphosis Testing (SAMT). We designed two metamorphic relations for test case generation. Using sequential sampling, we calculate the label stability rate and infer whether the image to be verified contains a backdoor based on the sequential probability ratio change. The experimental results show that our method has a higher backdoor detection success rate than the state-of-the-art universal adversarial perturbations detection algorithms. Moreover, our method does not need to use the model structure of deep neural networks, which has more adaptability and generalization ability. Based on our proposed method, we can simply add a backdoor detection layer to detect backdoors as early as possible, which can eventually alleviate the harm of such backdoors. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing: Serverless 12

Cloud Computing: Serverless

引用

12th International Conference on Information, Intelligence, Systems and Applications, IISA 2021

作者： Koschel, Arne Klassen, Samuel Jdiya, Kerim Schaaf, Marc Astrova, Irina University of Applied Sciences and Arts Hannover Faculty Iv Department of Computer Science Hannover Germany Institute of Information Systems University of Applied Sciences Northwestern Switzerland Olten Switzerland Tallinn University of Technology School of It Department of Software Science Tallinn Estonia

ISBN: (纸本)9781665400329

A serverless architecture is a new approach to offering services over the Internet. It combines BaaS (Backend-as-a-service) and FaaS (Function-as-a-service). With the serverless architecture no own or rented infrastructures are needed anymore. In addition, the company does not have to worry about scaling any longer, as this happens automatically and immediately. Furthermore, there is no need any longer for maintenance work on the servers, as this is completely taken over by the provider. Administrators are also no longer needed for the same reason. Finally, many ready-made functions are offered, with which the development effort can be reduced. As a result, the serverless architecture is very well suited to many application scenarios, and it can save considerable costs (server costs, maintenance costs, personnel costs, electricity costs, etc.). The company only must subdivide the source code of the application and upload it to the provider's server. The rest is done by the provider. © 2021 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths

arXiv

引用

arXiv 2022年

作者： Wen, Xin Xiang, Peng Han, Zhizhong Cao, Yan-Pei Wan, Pengfei Zheng, Wen Liu, Yu-Shen The School of Software Tsinghua University Beijing China The Department of Computer Science Wayne State University United States The School of Software BNRist Tsinghua University Beijing China The Y-tech Kuaishou Technology Beijing China JD Logistics *** China

Point cloud completion concerns to predict missing part for incomplete 3D shapes. A common strategy is to generate complete shape according to incomplete input. However, unordered nature of point clouds will degrade generation of high-quality 3D shapes, as detailed topology and structure of unordered points are hard to be captured during the generative process using an extracted latent code. We address this problem by formulating completion as point cloud deformation process. Specifically, we design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest. Therefore, PMP-Net++ predicts unique PMP for each point according to constraint of point moving distances. The network learns a strict and unique correspondence on point-level, and thus improves quality of predicted complete shape. Moreover, since moving points heavily relies on per-point features learned by network, we further introduce a transformer-enhanced representation learning network, which significantly improves completion performance of PMP-Net++. We conduct comprehensive experiments in shape completion, and further explore application on point cloud up-sampling, which demonstrate non-trivial improvement of PMP-Net++ over state-of-the-art point cloud completion/up-sampling methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Signal sampling

来源：评论

学校读者我要写书评

暂无评论

A Novel Cross-Perturbation for Single Domain Generalization

arXiv

引用

arXiv 2023年

作者： Zhao, Dongjia Qi, Lei Shi, Xiao Shi, Yinghuan Geng, Xin School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications [Southeast University Ministry of Education 211189 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. However, the limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. To address this, data perturbation (augmentation) has emerged as a crucial method to increase data diversity. Nevertheless, existing perturbation methods often focus on either image-level or feature-level perturbations independently, neglecting their synergistic effects. To overcome these limitations, we propose CPerb, a simple yet effective cross-perturbation method. Specifically, CPerb utilizes both horizontal and vertical operations. Horizontally, it applies image-level and feature-level perturbations to enhance the diversity of the training data, mitigating the issue of limited diversity in single-source domains. Vertically, it introduces multi-route perturbation to learn domain-invariant features from different perspectives of samples with the same semantic category, thereby enhancing the generalization capability of the model. Additionally, we propose MixPatch, a novel feature-level perturbation method that exploits local image style information to further diversify the training data. Extensive experiments on various benchmark datasets validate the effectiveness of our method. Copyright © 2023, 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

Efficient and Anonymous Authentication for Healthcare Service with Cloud Based WBANs

Efficient and Anonymous Authentication for Healthcare Servic...

引用

2021 IEEE World Congress on Services, SERVICES 2021

作者： Yang, Xu Yi, Xun Nepal, Surya Khalil, Ibrahim Huang, Xinyi Shen, Jian Fujian Normal University School Of Mathematics And Statistics Fuzhou China RMIT University School Of Computing Technologies Melbourne Australia CSIRO Data61 Sydney Australia Fujian Normal University College Of Computer And Cyber Security Fuzhou China Nanjing University Of Information Science And Technology School Of Computer And Software Jiangsu Nanjing China

ISBN: (纸本)9781665427197

Wireless body area networks (WBANs) technology nowadays has become a promising networking paradigm in the Internet of Things (IoT) as it can provide people with high quality of life and a high level of medical service. Specifically, to make sure those people with a high incidence of chronic diseases, including hypertension, diabetes, and cardiovascular diseases, are taking care of which further reduces social costs. Thus, both industry and academia in recent years pay widely attention to WBANs technology. After years of research, security, privacy, and efficiency of the healthcare services in WBANs have remained as major challenges. Although different authentication mechanisms have been designed to meet the challenges in recent years, most of them suffer from some functional defects or security problems. To ensure the security and privacy of patients' sensitive biomedical data and the efficiency of message processing across different devices, it is critical to provide a secure and lightweight authentication scheme for WBANs. © 2021 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A feedforward artificial neural network model for classification and detection of type 2 diabetes 1

A feedforward artificial neural network model for classifica...

引用

1st International Conference on Recent Trends in Applied Research, ICoRTAR 2020

作者： Frimpong, Enoch A. Oluwasanmi, Ariyo Baagyere, Edward Y. Zhiguang, Qin School of Information and Software Engineering University of Electronic Science and Technology of China No.4 North Jianshe Road Section 2 Chengdu Chengdu610054 China Department of Computer Science University for Development Studies Box TL 1350 Tamale Ghana

Efforts to enhance accuracy in medical diagnostics in molecular medicine have contributed to the wide use of artificial neural network (ANN) algorithms for disease detection due to its ability to process large medical datasets and integrate them into characterized outputs to avoid misdiagnosis. Typically, the application of ANNs have proven useful in sample analyses of patients with diabetes and in decision support systems. Over the years, various ANN models have been utilized in medical diagnostics;however, these approaches still maintain certain levels of error and have lesser training and testing accuracies in disease detection. In this study, we propose a Feedforward Artificial Neural Network (FFANN) model with a dense neural network architecture suitable for processing numeric and textual dataset. We carefully designed our model structure to have the ability to maximize the number of layers and nodes required to learn every feature of the dataset and also to perform effective computations but avoiding model under fitting and overfitting which occurs when less or more layers are used respectively. This approach puts our model ahead of other state-of-the-art prediction models which have been proposed in terms of performance as it achieved 97.27% and 96.09% training and testing accuracies, respectively, for type 2 diabetes detection on Pima Indian Diabetes dataset. © Published under licence by IOP Publishing Ltd.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

TechRxiv

引用

TechRxiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Software Engineering Sun Yat-Sen University Zhuhai China Department of Electrical and Computer Engineering Auburn University Auburn United States

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resource-intensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://***/Lizonghang/AGOD. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

STANet: Spatiotemporal Adaptive Network for Remote Sensing Images

STANet: Spatiotemporal Adaptive Network for Remote Sensing I...

引用

IEEE International Conference on Image Processing

作者： Chenlu Hu Mengting Ma Xiaowen Ma Huanting Zhang Dun Wu Guang Gao Wei Zhang School of Software Engineering Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Popsmart Technology (Zhejiang) Co. Ltd. Ningbo China Innovation Center of Yangtze River Delta Zhejiang University Jiaxing China

Spatiotemporal fusion aims to generate remote sensing images with high spatial and temporal resolutions. Conventional spatiotemporal fusion methods usually use convolution operations for feature extraction, which limits their capability of capturing long-range dependencies. Meanwhile, the significant difference of spatial resolutions of images brings great difficulty to the reconstruction of detailed textures. To address these issues, we propose a GAN-based multi-stage spatiotemporal adaptive network (STANet) for remote sensing images using temporal feature refinement and spatial texture transfer. In particular, we design a temporal interaction module (TIM) to extract useful information on surface changes over time, using a cross-temporal gating mechanism that emphasizes feature changes throughout the task. We employ the adaptive instance normalization (AdaIN) layers to learn the global spatial correlation via texture transfer from the fine image to the coarse image. Experiments on two datasets show that the proposed method outperforms other state-of-the-art methods in several metrics.

关键词：

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：