一种面向室内场景的语义分割网络

现有RGB D语义分割方法难以充分地融合深度信息来实现对复杂场景的语义分割,为了能更精确地在室内场景RGB图中进行识别内部物体,提出一种基于通道注意力机制的非对称三分支结构型卷积网络语义分割模型。该方法能选择性地从RGB图和深度图像中收集特征。先构建了一个具有三个并行分支的体系结构,并添加了三个互补的注意模块。且运用了双向跨模块特征传播策略,不仅可以保留原始RGB图像和深度图像的特征,还能充分利用融合分支的深度特征。在两个室内场景数据集(NYUDv2数据集和SUN RGBD数据集)进行了对照实验和消融研究。结果表明,所提出的模型与目前最好的表现方法注意力互补网络(ACNet)对比下,像素精度、平均像素精度、平均交并比分别提高了09、13、17,在镜子、书本、箱子等小物体的语义分割交并比指标提高了72、96、112。验证了提出的模型在处理室内场景具更强的适用性。     

Deep semantic image compression via cooperative network pruning

Incorporating semantic analysis into image compression can significantly reduce the repetitive computation of fundamental semantic analysis in downstream applications such as semantic image retrieval. In this paper, we tackle the semantic image compression task, which embeds semantics in the compressed bitstream. An intuitive solution to this task is joint multi-task training, which generally results in the trade-off of one task to accommodate the other. We thus provide an alternative pilot solution: given a pair of pre-trained teacher networks that specialize in image compression and semantic inference respectively, we first fuse both models to acquire an ensemble model and then leverage cooperative network pruning and retraining to condense the knowledge. Various experiments on five benchmark datasets validate that the proposed method achieves on par and in many cases better performance than the teachers yet comes in a more compact size, and outperforms its multi-task learning and knowledge distillation counterparts.     

Evaluation and application of a semantic network partition

Semantic networks (SNs) are excellent knowledge representation structures. However, large semantic networks are difficult to comprehend. To overcome this difficulty, several methods of partitioning have been developed that rely on different mixes of structural and semantic methods. However, little has appeared in the literature concerning the question whether a partition of a semantic network creates subnetworks that agree with human insight. We address this issue by presenting a comparison between the results of an algorithmic partitioning method and a partition created by a group of experts. Subsequently, we show how a network partition can be used to generate various partial views of a semantic network, which facilitate user orientation. Examples from the Unified Medical Language System (UMLS) SN are used to demonstrate partial views     

网络数据库访问中语义指向性算法优化

为解决数据库从高维单词空间映射至低维隐含语义空间中,无法有效实现数据库访问语义指向性分析的问题,提出基于主题模型的数据库访问语义指向性算法,建立PLSA主体模型并对其进行求解,通过PLSA主题模型获取理想的潜在语义主题,在数据库访问关键词上分布以及文档在潜在语义主题上的分布,将其应用于数据库访问语义指向性分析中,针对数据库表现出来的文本特征和结构特征建立PLSA主题模型,通过自适应不对称学习算法对不同的PLSA主题模型进行集成和优化,以实现数据库访问语义指向性分析,使数据库访问结果更加准确。仿真实验结果表明所提算法具有很高的数据库访问效率及精度。     

语义网在网络检索中的发展趋势

通过介绍语义网的相关概念、特点，分析语义网如何能够在网络检索中完成令人满意的精确、智能检索．并对语义网所面临的问题和发展前景进行描述。     

基于深度卷积神经网络的图像语义分割

近年来,以深度卷积神经网络(DEEP Convolutional Neural Network,DCNN)为代表结合条件随机场(Conditional Random Field,CRF)的深度学习算法在图像分割领域中有非常出色的表现。文中首先介绍传统的深度卷积神经网络在图像分割中面临的三个问题以及所借鉴的相关理论;其次介绍对传统深度卷积神经网络三个方面的改进;最后是本次实验的结果和分析。     

SSCAN:一种安全的基于CAN的语义网络

现有的基于DHT（Distributed Hash Table）模型的P2P网络并不能很好支持语义查询,只提供针对某个关键字单一的准确查询,为了实现语义搜索,人们提出若干基于VSM的改进方案,而这些模型存在各种问题。本文首次分析了P2P中语义网络可能存在的安全问题,阐述了哈希算法和语义网络之间的固有矛盾;构建一个支持语义搜索的安全CAN网络SSCAN（Secure and Semantic CAN）,设计了一种在SSCAN中进行语义搜索的算法,并对搜索性能进行评估。该模型具有安全性高,搜索高效的特点。     

基于扩展的语义网络的过程知识表示的研究

文中研究基于语义网络的知识表示,针对目前语义网络框架无法表示过程知识等复杂知识的缺陷,提出了一种称为抽象语义网络的扩展的语义网络,以及基于抽象语义网络的图变换,主要研究了该扩展的语义网络如何表示过程知识,以及利用图变换实现语义网络上的过程变换。     

基于编码-解码神经网络遥感图像语义分割应用研究

图像分割的实现经历了从传统方法到神经网络方法的演变.本文从图像分割的发展过程入手,介绍了图像分割与语义分割的区别,对最近几年传统图像分割方法在遥感图像分割领域的应用进行梳理分析,总结了传统遥感图像分割方法的不足.基于此,归纳了几种经典编码-解码神经网络架构在遥感图像语义分割领域的应用,对其改进方式进行了综合性分析,并对...     

基于关系模型的语义网络知识表示研究

关系数据库理论基础坚实、技术成熟、产品丰富,多年来一直是存储和处理大数据量的研究和应用首选。如何在关系数据库强大的存储和处理能力基础上建立知识库,一直是知识工程和智能系统研究与应用人员重点研究的内容,也是知识管理走向应用的技术瓶颈。文中提出了语义网络的关系模型,并用实例论述了语义网络知识的关系数据表的存储。     

Low-light image enhancement algorithm using a residual network with semantic information

Aiming to solve the poor performance of low illumination enhancement algorithms on uneven illumination images, a low-light image enhancement(LIME) algorithm based on a residual network was proposed. The algorithm constructs a deep network that uses residual modules to extract image feature information and semantic modules to extract image semantic information from different levels. Moreover, a composite loss function was also designed for the process of low illumination image enhancement, which ...     

Web网络环境下的语义检索平台设计与分析

在Web网络环境下,传统信息检索方法仅依据简单的字和词进行匹配,未考虑知识的描述、处理以及理解等性能,检索质量和效率低。因此,设计了基于Web的语义检索平台,其由数据层、数据访问层、业务逻辑层、控制层和人机接口层组成。业务逻辑层依据数据访问层操作数据,并将数据反馈给控制层;控制层是用户申请和业务逻辑操作间的调控器;人机接口层是用户同检索平台间实现交互的桥梁,用户通过该层中的操作界面完成信息的检索。分析Jena在语义检索平台中的作用,并在软件设计部分,分析通过Jena实现语义检索平台数据检索的过程和其中的关键代码。实验结果表明所设计的语义检索平台具有较高的检索质量和效率。     

Study on traffic scene semantic segmentation method based on convolutional neural network

In order to improve the semantic segmentation accuracy of traffic scene,a segmentation method was proposed based on RGB-D image and convolutional neural network.Firstly,on the basis of semi-global stereo matching algorithm,the disparity map was obtained,and the sample library was established by fusing the disparity map D and RGB image into the four-channel RGB-D image.Then,with two different structures,the networks were trained by using two different learning rate adjustment strategy respectively.Finally,the traffic scene semantic segmentation test was carried out with RGB-D image as the input,and the results were compared with the segmentation method based on RGB image.The experimental results show that the proposed traffic scene segmentation algorithm based on RGB-D image can achieve higher semantic segmentation accuracy than that based on RGB image.     

基于铆钉表面缺陷检测的语义分割网络研究

本文基于U-net++基本网络结构,结合铆钉表面缺陷检测的特点,设计了一个语义分割网络模型。首先,对标注数据集进行模糊标签处理,增强了网络对缺陷的学习能力,有效解决了铆钉缺陷边界确定难的问题。然后,考虑到铆钉语义层次的特点,对原始网络结构进行剪枝,减少下采样的次数,以满足系统对实时性的要求。最后,设计了复合损失函数,以促进小样本缺陷的学习速度,解决了采用单一交叉熵损失函数在缺陷较小的数据集中收敛慢的问题。在对比试验中,本文提出方法均展现出较好的效果。     

MSN: statistical understanding of broadcasted baseball video using multi-level semantic network

The information processing of sports video yields valuable semantics for content delivery over narrowband networks. Traditional image/video processing is formulated in terms of low-level features describing image/video structure and intensity, while the high-level knowledge such as common sense and human perceptual knowledge are encoded in abstract and nongeometric representations. The management of semantic information in video becomes more and more difficult because of the large difference in representations, levels of knowledge, and abstract episodes. This paper proposes a semantic highlight detection scheme using a Multi-level Semantic Network (MSN) for baseball video interpretation. The probabilistic structure can be applied for highlight detection and shot classification. Satisfactory results will be shown to illustrate better performance compared with the traditional ones.     

结合局部增强与反向残差的点云语义分割网络北大核心CSCD

激光点云是3D传感器的输出,且对它的语义分割任务是理解真实世界的基础。基于图卷积的点云分割网络在许多场景下都展现了优异的性能。然而,现有的图卷积方法存在部分问题:点云局部表示的能力未得到加强,忽略了全局几何信息,并且聚合操作只保留局部最大响应值信息,而次最大值信息丢失。为了处理这些问题,本文提出GRes-Net网络。利用局部几何加强(Local Geometry Augment,LGA)模块,使网络对Z轴具有旋转不变性,以便加强点云局部信息表示;采用全局几何特征(Global Geometry Feature,GGF)模块,计算局部与全局的球体体积比,将其与坐标特征X进行连接,使全局几何信息特征得以保留;通过多个对称聚合操作将局部信息多方面地保留;网络中每层都使用残差操作,将上一层信息传递到下一层,以及利用反向残差模块(Reversed Residual MLP,RevResMLP)挖掘更深层次的语义信息。本文在S3DIS数据集上进行语义场景分割实验,验证网络分割的性能。实验结果表明该方法在分割精度上达到61%,相比于基准网络DGCNN提高14%,有效地提高了模型性能。     

Two-Phase Chief Complaint Mapping to the UMLS Metathesaurus in Korean Electronic Medical Records

The task of automatically determining the concepts referred to in chief complaint (CC) data from electronic medical records (EMRs) is an essential component of many EMR applications aimed at biosurveillance for disease outbreaks. Previous approaches that have been used for this concept mapping have mainly relied on term-level matching, whereby the medical terms in the raw text and their synonyms are matched with concepts in a terminology database. These previous approaches, however, have shortcomings that limit their efficacy in CC concept mapping, where the concepts for CC data are often represented by associative terms rather than by synonyms. Therefore, herein we propose a concept mapping scheme based on a two-phase matching approach, especially for application to Korean CCs, which uses term-level complete matching in the first phase and concept-level matching based on concept learning in the second phase. The proposed concept-level matching suggests the method to learn all the terms (associative terms as well as synonyms) that represent the concept and predict the most probable concept for a CC based on the learned terms. Experiments on 1204 CCs extracted from 15 618 discharge summaries of Korean EMRs showed that the proposed method gave significantly improved F-measure values compared to the baseline system, with improvements of up to 73.57%.     

基于语义特征传播图神经网络的小样本图像分类算法

使用少量样本进行学习和概括的能力是人工智能和人类之间主要的区别。在小样本学习领域,大多数图神经网络专注于将标记的样本信息传递给未标记的查询样本,而忽略了语义特征在分类过程中的重要作用。为此构建了语义特征传播图神经网络,首先将语义特征嵌入到图神经网络中,解决了细粒度图像特征相似性带来的分类准确率低的问题,然后将注意力机制与骨干网络合并达到强化前景并提高特征提取质量的目的,利用马氏距离计算类的相似度得到更好的分类性能,最后使用Funnel ReLU函数作为激活函数进一步提高分类准确率。在基准数据集上实验表明,所提算法相比于基线算法在5类1/2/5样本任务上的准确率分别提高了903%、456%和415%。     

一种基于协同过滤与语义分析的个性化网络广告投放方法研究

针对个性化网络广告中网页与广告匹配的问题,通过将基于关键词扩展的语义分析技术引入到协同过滤系统中,提出一种基于协同过滤与语义分析结合的个性化网络广告投放方法(CFKE)。该方法首先提取网页与广告文本的关键词,并对关键词扩展同义词;然后,计算网页扩展词与广告扩展词的相似度,并与扩展词的权重进行拟合抽取,得到网页与广告最终的相似度,将三维模型降维成二维模型;最后,再利用协同过滤方法进行匹配。仿真表明,与其他算法相比,该算法不仅具有较高的准确度,同时具有较好的系统响应能力。