检索结果-内蒙古大学图书馆

4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Oversampling Multi-Label data Based on Natural Neighbor and Label Correlation

SSRN

引用

SSRN 2023年

作者： Liu, Bin Zhou, Ao Wang, Jin Tsoumakas, Grigorios Key Laboratory of Data Engineering and Visual Computing School of Computer Science of Technology Chongqing University of Posts and Telecommunications Chongqing400065 China School of Informatics Aristotle University of Thessaloniki Thessaloniki54124 Greece

In multi-label learning, addressing the class imbalance issue is of paramount importance. Oversampling methods are preferred as they offer a more general solution independent of the model choice, i.e., they alleviate the imbalance of datasets by augmenting instances in the pre-processing step. Existing neighbor-based oversampling methods employ an empirical number of neighbors (k=5), to identify the local region for new instances creation. However, a single fixed k value cannot fit all labels, because every label usually has its own distinct distribution and complexity. Furthermore, the label assignment for synthetic instances usually depends on the statistics of individual labels within the corresponding neighborhood, ignoring the informative correlation among labels. To overcome these limitations, we propose an oversampling method called Multi-Label Oversampling with Natural neighbor and label Correlation (MLONC). Our approach offers three main advantages: 1) the adaptive number of neighbors for each label related to the data complexity is obtained via natural neighbor detection;2) it encourages generating more instances proximate to the decision boundary of highly imbalanced labels, and diminishes the impact of outliers;3) exploitation of label correlation in label assignment enhances the quality of the synthetic instances. Experimental results demonstrate the effectiveness of MLONC under various base classifiers. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multilingual Knowledge Graph Completion via Multimodal Decouple and Relation-based Ensemble Inference 29

Multilingual Knowledge Graph Completion via Multimodal Decou...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Liu, Xiaojing Jiang, Xuesong Yi, Fengge Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

The objective of Multimodal Knowledge Graph Completion (MKGC) is to forecast absent entities within a knowledge graph by leveraging additional textual and visual modalities. Existing studies commonly utilize a singular relationship embedding to depict all modalities within an entity pair, thus connecting several relationships derived from diverse modalities. However, this coupling may introduce interference from conflicting information between modalities, as the relationships between modalities for a given entity pair can be contradictory. Moreover, existing Ensemble Inference methods fail to dynamically adjust modal weights based on their differences and importance, despite the varying contributions of different modalities. In this paper, we propose the Multimodal Decouple and Relation-based Ensemble inference (MDRE) model. For each modality, we construct corresponding relationship embeddings and build separate triple representations to avoid interferences among modalities. During the training phase, we employ confidence-constrained training with temperature scaling to alleviate conflicting information in textual and visual modalities. For inference, we utilize the Relation-based Ensemble Inference method to adjust modal weights at the relationship level, thus achieving improved prediction results. Experimental results on two datasets demonstrate that MDRE outperforms existing single-modal and multimodal knowledge graph completion methods in terms of performance. © 2023 IEEE.

关键词： knowledge graph knowledge graph completion multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Abnormality Detection in Chest X-Ray Images Using Uncertainty Prediction Autoencoders 23rd

Abnormality Detection in Chest X-Ray Images Using Uncertaint...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Mao, Yifan Xue, Fei-Fei Wang, Ruixuan Zhang, Jianguo Zheng, Wei-Shi Liu, Hongmei School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Pazhou Lab Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (纸本)9783030597245

Chest radiography is widely used in annual medical screening to check whether lungs are healthy or not. Therefore it would be desirable to develop an intelligent system to help clinicians automatically detect potential abnormalities in chest X-ray images. Here with only healthy X-ray images, we propose a new abnormality detection approach based on an autoencoder which outputs not only the reconstructed normal version of the input image but also a pixel-wise uncertainty prediction. Higher uncertainty often appears at normal region boundaries with relatively larger reconstruction errors, but not at potential abnormal regions in the lung area. Therefore the normalized reconstruction error by the uncertainty provides a natural measurement for abnormality detection in images. Experiments on two chest X-ray datasets show the state-of-the-art performance by the proposed approach. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Distributed Framework for Large-scale Protein-protein Interaction data Analysis and Prediction Using MapReduce

引用

IEEE/CAA Journal of Automatica Sinica 2022年第1期9卷 160-172页

作者： Lun Hu Shicheng Yang Xin Luo Huaqiang Yuan Khaled Sedraoui MengChu Zhou School of Computer Science and Technology Dongguan University of TechnologyDongguan 523808China School of Computer Science and Technology Wuhan University of TechnologyWuhan 430070China Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent ComputingChongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of SciencesUrumqi 830000China Center of Research Excellence in Renewable Energy and Power Systems and the Department of Electrical and Computer EngineeringFaculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA

Protein-protein interactions are of great significance for human to understand the functional mechanisms of *** the rapid development of high-throughput genomic technologies,massive protein-protein interaction(PPI)data have been generated,making it very difficult to analyze them *** address this problem,this paper presents a distributed framework by reimplementing one of state-of-the-art algorithms,i.e.,CoFex,using *** do so,an in-depth analysis of its limitations is conducted from the perspectives of efficiency and memory consumption when applying it for large-scale PPI data analysis and *** solutions are then devised to overcome these *** particular,we adopt a novel tree-based data structure to reduce the heavy memory consumption caused by the huge sequence information of *** that,its procedure is modified by following the MapReduce framework to take the prediction task distributively.A series of extensive experiments have been conducted to evaluate the performance of our framework in terms of both efficiency and *** results well demonstrate that the proposed framework can considerably improve its computational efficiency by more than two orders of magnitude while retaining the same high accuracy.

关键词： Distributed computing large-scale prediction machine learning MapReduce protein-protein interaction(PPI)

来源：评论

学校读者我要写书评

暂无评论

M-DFCPP: A runtime library for multi-machine dataflow computing

M-DFCPP: A runtime library for multi-machine dataflow comput...

引用

作者： Luo, Qiuming Liu, Senhong Huang, Jinke Li, Jinrong College of Computer Science and Software Engineering Shenzhen University Shenzhen China SKT Group Guangdong Province Key Laboratory of Popular High-Performance Computers Shenzhen China SKT Group Guangdong Province Engineering Center of China-made High Performance Data Computing System Shenzhen China

This article designs and implements a runtime library for general dataflow programming, DFCPP (Luo Q, Huang J, Li J, Du Z. Proceedings of the 52nd International Conference on Parallel Processing Workshops. ACM;2023:145-152.), and builds upon it to design and implement a multi-machine C++ dataflow library, M-DFCPP. In comparison to existing dataflow programming environments, DFCPP features a user-friendly interface and richer expressive capabilities (Luo Q, Huang J, Li J, Du Z. Proceedings of the 52nd International Conference on Parallel Processing Workshops. ACM;2023:145-152.), enabling the representation of various types of dataflow actor tasks (static, dynamic and conditional task). Besides that, DFCPP addresses the memory management and task scheduling for non-uniform memory access architectures, while other dataflow libraries lack attention to these issues. M-DFCPP extends the capability of current dataflow runtime libraries (DFCPP, taskflow, openstream, etc.) and capable of multi-machine computing, while maintains the API compatible with DFCPP. M-DFCPP adopts the concepts of master and follower (Dean J, Ghemawat S. Commun ACM. 2008;51(1):107-113;Ghemawat S, Gobioff H, Leung ST. ACM SIGOPS Operating Systems Review. ACM;2003:29-43.), which form a worksharing framework as many multi-machine system. To shift to the M-DFCPP framework, a filtering layer is inserted to the original DFCPP, transforming it into followers that can cooperate with each other. The master is made of modules for scheduling, data processing, graph partition, state management and so forth. In benchmark tests with workload with directed acyclic graph topology of binary trees and random graphs, DFCPP demonstrated performance improvements of 20% and 8%, respectively, compared to the second fastest library. M-DFCPP consistently exhibits outstanding performance across varying levels of concurrency and task workloads, achieving a maximum speedup of more than 20 over DFCPP, when the task parallelism e

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Container lifecycle-aware scheduling for serverless computing

Container lifecycle-aware scheduling for serverless computin...

引用

作者： Wu, Song Tao, Zhiheng Fan, Hao Huang, Zhuo Zhang, Xinmin Jin, Hai Yu, Chen Cao, Chun National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Elastic scaling in response to changes on demand is a main benefit of serverless computing. When bursty workloads arrive, a serverless platform launches many new containers and initializes function environments (known as cold starts), which incurs significant startup latency. To reduce cold starts, platforms usually pause a container after it serves a request, and reuse this container for subsequent requests. However, this reuse strategy cannot efficiently reduce cold starts because the schedulers are agnostic of container lifecycle. For example, it may ignore soon available containers or evict soon needed containers. We propose a container lifecycle-aware scheduling strategy for serverless computing, CAS. The key idea is to control distribution of requests and determine creation or eviction of containers according to different lifecycle phases of containers. We implement a prototype of CAS on OpenWhisk. Our evaluation shows that CAS reduces 81% cold starts and therefore brings a 63% reduction at 95th percentile latency compared with native scheduling strategy in OpenWhisk when there is worker contention between workloads, and does not add significant performance overhead. © 2021 John Wiley & Sons Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

EdgeNN: Efficient Neural Network Inference for CPU-GPU Integrated Edge Devices

EdgeNN: Efficient Neural Network Inference for CPU-GPU Integ...

引用

International Conference on data engineering

作者： Chenyang Zhang Feng Zhang Kuangyu Chen Mingjun Chen Bingsheng He Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China School of Computing National University of Singapore

With the development of the architectures and the growth of AIoT application requirements, data processing on edge has become popular. Neural network inference is widely employed for data analytics on edge devices. This paper extensively explores neural network inference on integrated edge devices and proposes EdgeNN, the first neural network inference solution on CPU-GPU integrated edge devices. EdgeNN has three novel characteristics. First, EdgeNN can adaptively utilize the unified physical memory and conduct the zero-copy optimization. Second, EdgeNN involves a novel inference-targeted inter- and intra-kernel CPU-GPU hybrid execution approach, which co-runs the CPU with the GPU to fully utilize the edge device’s computing resources. Third, EdgeNN adopts a fine-grained adaptive inference tuning approach, which can divide the complicated inference structure into sub-tasks mapped to the CPU and the GPU. Experiments show that on six popular neural network inference tasks, EdgeNN brings an average of 3.97×, 3.12×, and 8.80× speedups to inference on the CPU of the integrated device, inference on a mobile phone CPU, and inference on an edge CPU device. Additionally, it achieves 22.02% time benefits to the direct execution of the original programs. Specifically, 9.93% comes from better utilization of unified memory, and 10.76% comes from CPU-GPU hybrid execution. Besides, EdgeNN can deliver 29.14× and 5.70× higher energy efficiency than the edge CPU and the discrete GPU, respectively. We have made EdgeNN available at https://***/ChenyangZhang-cs/EdgeNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges in Chinese knowledge graph construction

Challenges in Chinese knowledge graph construction

引用

International Conference on data engineering Workshops

作者： Chengyu Wang Ming Gao Xiaofeng He Rong Zhang Shanghai Key Laboratory of Trustworthy Computing Data Science and Engineering Institute East China Normal University Shanghai China

ISBN: (纸本)9781479984435

The automatic construction of large-scale knowledge graphs has received much attention from both academia and industry in the past few years. Notable knowledge graph systems include Google Knowledge Graph, DBPedia, YAGO, NELL, Probase and many others. Knowledge graph organizes the information in a structured way by explicitly describing the relations among entities. Since entity identification and relation extraction are highly depending on language itself, data sources largely determine the way the data are processed, relations are extracted, and ultimately how knowledge graphs are formed, which deeply involves the analysis of lexicon, syntax and semantics of the content. Currently, much progress has been made for knowledge graphs in English language. In this paper, we discuss the challenges facing Chinese knowledge graph construction because Chinese is significantly different from English in various linguistic perspectives. Specifically, we analyze the challenges from three aspects: data sources, taxonomy derivation and knowledge extraction. We also present our insights in addressing these challenges.

关键词： Encyclopedias Internet Electronic publishing Taxonomy Semantics data mining

来源：评论

学校读者我要写书评

暂无评论

Intelligent Question and Answering System Based on SVM and Cosine Similarity

Intelligent Question and Answering System Based on SVM and C...

引用

2017 International Conference on Mathematics, Modelling and Simulation Technologies and Applications（MMSTA 2017)

作者： Wan-li SONG Wei-wei CHEN Ming-zhu ZHANG Key Laboratory of Trusted Cloud Computing and Big Data Analysis School of Information EngineeringNanjing Xiao Zhuang University

It is a tough task for teachers to answer all questions from students effectively and *** this paper,we design and implements an intelligent question answering system using Natural Language Processing,template classification,support vector *** system also calculates the similarity between the question and answer pairs by cosine similarity algorithm,and returns the most similar *** the user is not satisfied with the answer,the system will write the question into the public section to fall back on other *** answer will be evaluated and added to the QA base if it is passed with the corresponding *** that the questions and answers in the QA base continue to *** use the QA base of a network forum as the basic library to carry out the *** implementation and experimental results indicate that the proposed approach is achievable.

关键词： Intelligent system Question classification Question similarity Cosine similarity

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：