检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Guo, Suhan Lai, Bilan Yang, Suorong Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Department of Computer Science and Technology Nanjing University China School of Electronic Science and Engineering Nanjing University China

As neural networks get deeper to better higher performance, the demand for deployable models on resource-constrained devices also grows. In this work, we propose to achieve model compression using filter-level pruning, which eliminates less sensitive filters. The previous method evaluates neuron importance using the connection matrix gradient in a single shot, which is vulnerable to the sampling bias. Thus, we integrate this measure with the previously proposed "pruning while fine-tuning" framework. Besides classification errors, we introduce the difference between the learned pruning strategy and the single-shot strategy as the second loss component with a self-adjustive hyper-parameter that balances the training goal between improving accuracy and pruning more filters. Experimental results demonstrate the effectiveness of our Sensitivity Pruner (SP), which significantly reduces the computational cost and makes pruned models achieve comparable if not better performance on CIFAR10, CIFAR100, and ILSVRC-12 datasets. © 2022, 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

Vehicle Matching Based on Similarity Metric Learning

引用

Journal of New Media 2022年第1期4卷 51-58页

作者： Yujiang Li Chun Ding Zhili Zhou Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information ScienceandTechnologyNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China

With the development of new media technology,vehicle matching plays a further significant role in video surveillance *** methods explored the vehicle matching based on the feature ***,similarity metric learning also has achieved enormous progress in vehicle *** most of these methods are less effective in some realistic scenarios where vehicles usually be captured in different *** address this cross-domain problem,we propose a cross-domain similarity metric learning method that utilizes theGANto generate vehicle imageswith another domain and propose the two-channel Siamese network to learn a similarity metric from both domains(i.e.,Day pattern or Night pattern)for vehicle *** exploit properties and relationships among vehicle datasets,we first apply the domain transformer to translate the domain of vehicle images,and then utilize the two-channel Siamese network to extract features from both domains for better feature similarity *** results illustrate that our models achieve improvements over state-of-the-arts.

关键词： Vehicle matching cross-domain similarity metric learning two-channelsiamesenetwork

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Intrusion Detection Performance Evaluation and Comparative Analysis

Machine Learning Algorithms for Intrusion Detection Performa...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： B. Md. Irfan V. Poornima S Mohana Kumar Upendra Singh Aswal N. Krishnamoorthy Ramya Maranan Department of Information Technology Nalsar University of Law Hyderabad Telengana India Department of Computer Science VISTASPallavaram Chennai Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru Karnataka India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Software Systems and Engineering Vellore Institute of Technology Vellore Campus Vellore Tamilnadu Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

The security of computer networks is increasingly difficult to maintain due to the rising complexity and frequency of cyber-attacks. Important tools for finding and neutralizing these dangers are intrusion detection systems. This study sets out to do a thorough examination and comparison of the efficacy of several machine learning algorithms for use in intrusion detection. This research study evaluates the efficacy of several machine learning algorithms in correctly categorizing instances of network traffic as normal or invasive via extensive experiments performed on representative datasets. Algorithms like random forests, decision trees, SVMs, DL models and NNs are all being tested and rated. Effectiveness is measured and compared using a variety of performance indicators including accuracy, recall, precision, false positive rate, and F1-score. The results of this study emphasize the potential of deep learning models and Random Forests for use in intrusion detection and add to the body of knowledge around machine learning methods for this task. Professionals in the field of network security might use the results to their advantage when building intrusion detection systems. Future research areas are also mentioned, which will hopefully lead to even greater improvements in the field and safer, more reliable intrusion detection systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Testing Microservice Systems

On Testing Microservice Systems

引用

Future Technologies Conference, FTC 2020

作者： Koschel, Arne Astrova, Irina Bartels, Mirco Helmers, Mark Lyko, Marcel Faculty IV Department of Computer Science University of Applied Sciences and Arts Hannover Ricklinger Stadtweg 120 Hannover30459 Germany Department of Software Science School of IT Tallinn University of Technology Akadeemia tee 21 Tallinn12618 Estonia

ISBN: (纸本)9783030630911

Microservices gain more and more importance and are already widely used in many software systems. While using a microservice architecture can bring a lot of benefits, there are also lots of new challenges arising. The general complexity of loosely coupled microservice systems is higher than in mono-lithic software systems. As a result, the testing of microservice systems can be more difficult and calls for additional testing methods and techniques. Furthermore, the usage of additional testing tools is recommended. © 2021, Springer Nature Switzerland AG.

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

Putting Robots in Context: Challenging the Influence of Voice and Empathic Behaviour on Trust

Putting Robots in Context: Challenging the Influence of Voic...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Marta Romeo Ilaria Torre Sébastien Le Maguer Angelo Cangelosi Iolanda Leite School of Mathematical and Computer Sciences Heriot-Watt University Edinburgh UK School of Computer Science University of Manchester Manchester UK Division of Interaction Design and Software Engineering Chalmers University of Technology Gothenburg Sweden Division of Robotics Perception and Learning KTH Royal Institute of Technology Stockholm Sweden ADAPT Centre Trinity College Dublin Dublin Ireland

Trust is essential for social interactions, including those between humans and social artificial agents, such as robots. Several robot-related factors can contribute to the formation of trust. However, previous work has often treated trust as an absolute concept, whereas it is highly context-dependent, and it is possible that some robot-related features will influence trust in some contexts, but not in others. In this paper, we present the results of two video-based online studies aimed at investigating the role of robot voice and empathic behaviour on trust formation in a general context as well as in a task-specific context. We found that voice influences trust in the specific context, with no effect of voice or empathic behaviour in the general context. Thus, context mediated whether robot-related features play a role in people’s trust formation towards robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Trusted Architecture and Service Mechanisms based on SylixOS

A Lightweight Trusted Architecture and Service Mechanisms ba...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Qidi Zhao Hongjun You Tianyang Wang Changyi Du Bohao Pei Kailong Zhang School of Computer Science Northwestern Polytechnical University Xi'an China Shanghai Aerospace Electronic Technology Institute Shanghai China School of Software Northwestern Polytechnical University Xi'an China

With the advent of the Internet of Things (IoT), more and more embedded systems have been becoming networked and autonomous, however, which also brings a serious challenge to security. After analyzing the theory about trusted computing and dependable characteristics of embedded systems, in this paper, a lightweight trusted architecture has been studied, and further, several service mechanisms are proposed. In this architecture, trusted software base with whitelists is firstly established as the key foundation. On this basis, two main mechanisms: identity authentication of legal tasks and permission management of legal tasks, are designed for guaranteeing the running-time trust of an embedded system. Through the previous mechanism, any illegal task could be detected and prohibited in real-time. And via the latter, the behavior of any legal task could be restricted in the right range during its running. Finally, all these designs have been implemented within SylixOS as lightweight trusted services, and further, verified with several typical test cases we designed. In general, the thought of this work can also be a general and feasible reference for the development of trusted embedded systems running in a networked environment.

关键词： Trusted computing Embedded systems Law computer architecture Real-time systems software Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Image

CM-MLP: Cascade Multi-scale MLP with Axial Context Relation ...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Lv, Jinkai Hu, Yuyong Fu, Quanshui Zhang, Zhiwang Hu, Yuqiang Lv, Lin Yang, Guoqing Li, Jinpeng Zhao, Yi Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China The Research Center for Ubiquitous Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing China Suining Central Hospital Suining China Hwa Mei Hospital University of Chinese Academy of Sciences Ningbo China School of Electrical and Information Engineering The University of Sydney Sydney Australia School of Mathematics and Computer Sciences NanChang University Nanchang China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665468190

The convolutional-based methods provide good segmentation performance in the medical image segmentation task. However, those methods have the following challenges when dealing with the edges of the medical images: (1) Previous convolutional-based methods do not focus on the boundary relationship between foreground and background around the segmentation edge, which leads to the degradation of segmentation performance when the edge changes complexly. (2) The inductive bias of the convolutional layer cannot be adapted to complex edge changes and the aggregation of multiple-segmented areas, resulting in its performance improvement mostly limited to segmenting the body of segmented areas instead of the edge. To address these challenges, we propose the CM-MLP framework on MFI (Multiscale Feature Interaction) block and ACRE (axial context relation encoder) block for accurate segmentation of the edge of medical image. In the MFI block, we propose the cascade multi-scale MLP (Cascade MLP) to process all local information from the deeper layers of the network simultaneously and utilize a cascade multiscale mechanism to fuse discrete local information gradually. Then, the ACRE block is used to make the deep supervision focus on exploring the boundary relationship between foreground and background to modify the edge of the medical image. The segmentation accuracy (Dice) of our proposed CM-MLP framework reaches 96.96%, 96.76%, and 82.54% on three benchmark datasets: CVC-ClinicDB dataset, sub-Kvasir dataset, and our inhouse dataset, respectively, which significantly outperform the state-of-the-art method. The source code and trained models will be available at https://***/ProgrammerHyy/CM-MLP. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing

arXiv

引用

arXiv 2022年

作者： Nie, Lunyiu Sun, Jiuding Wang, Yanlin Du, Lun Hou, Lei Li, Juanzi Han, Shi Zhang, Dongmei Zhai, Jidong Department of Computer Science and Technology Tsinghua University China School of Software Engineering Sun Yat-Sen University China Microsoft Research Asia China

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task. Despite the promising performance, previous PLM-based approaches often suffer from hallucination problems due to their negligence of the structural information contained in the sentence, which essentially constitutes the key semantics of the logical forms. Furthermore, most works treat PLM as a black box in which the generation process of the target logical form is hidden beneath the decoder modules, which greatly hinders the model’s intrinsic interpretability. To address these two issues, we propose to incorporate the current PLMs with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks, namely Semantic Anchor Extraction and Semantic Anchor Alignment, for training the hierarchical decoders and probing the model intermediate representations in a self-adaptive manner alongside the fine-tuning process. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines. More importantly, by analyzing the intermediate representations of the hierarchical decoders, our approach also makes a huge step toward the intrinsic interpretability of PLMs in the domain of semantic parsing. © 2022, CC BY-SA.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Efficient reversible data hiding via two layers of double-peak embedding

arXiv

引用

arXiv 2022年

作者： Wu, Fuhu Sun, Jian Zhang, Shun Chen, Zhili School of Computer Science and Technology Anhui University Hefei230601 China Software Engineering Institute East China Normal University Shanghai200062 China

Reversible data hiding continues to attract significant attention in recent years. In particular, an increasing number of authors focus on the higher significant bit (HSB) plane of an image which can yield more redundant space. On the other hand, the lower significant bit plane is often discarded in existing schemes due to their harm to the embedding rate. This paper proposes an efficient reversible data hiding scheme via a double-peak two-layer embedding (DTLE) strategy with prediction error expansion. The higher six-bit planes of the image are assigned as the HSB plane, and double prediction error peaks are applied in either embedding layer. This makes fuller use of the redundancy space of images compared with the one error peak strategy. Moreover, we carry out the median-edge detector pre-processing for complex images to reduce the size of the auxiliary information. A series of experimental results show that our DTLE approach achieves up to 83% higher embedding rate on real-world data while providing better image quality. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

arXiv

引用

arXiv 2023年

作者： Li, Qing Feng, Huifang Shi, Kanle Gao, Yue Fang, Yi Liu, Yu-Shen Han, Zhizhong School of Software Tsinghua University Beijing China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China School of Computer and Software Engineering Xihua University Chengdu China Kuaishou Technology Beijing China Center for Artificial Intelligence and Robotics New York University Abu Dhabi Abu Dhabi United Arab Emirates Department of Computer Science Wayne State University Detroit United States

We propose a novel method called SHS-Net for point cloud normal estimation by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipeline, i.e., unoriented normal estimation and normal orientation, and each step is implemented by a separate algorithm. However, previous methods are sensitive to parameter settings, resulting in poor results from point clouds with noise, density variations and complex geometries. In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. Specifically, we introduce a patch encoding module and a shape encoding module to encode a 3D point cloud into a local latent code and a global latent code, respectively. Then, an attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals. Experimental results show that our algorithm outperforms the state-of-the-art methods in both unoriented and oriented normal estimation. © 2023, CC BY-NC-SA.

关键词： Surface reconstruction

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：