共查询到20条相似文献,搜索用时 93 毫秒
1.
目的 现有的深度学习模型往往需要大规模的训练数据,而小样本分类旨在识别只有少量带标签样本的目标类别。作为目前小样本学习的主流方法,基于度量的元学习方法在训练阶段大多没有使用小样本目标类的样本,导致这些模型的特征表示不能很好地泛化到目标类。为了提高基于元学习的小样本图像识别方法的泛化能力,本文提出了基于类别语义相似性监督的小样本图像识别方法。方法 采用经典的词嵌入模型GloVe(global vectors for word representation)学习得到图像数据集每个类别英文名称的词嵌入向量,利用类别词嵌入向量之间的余弦距离表示类别语义相似度。通过把类别之间的语义相关性作为先验知识进行整合,在模型训练阶段引入类别之间的语义相似性度量作为额外的监督信息,训练一个更具类别样本特征约束能力和泛化能力的特征表示。结果 在miniImageNet和tieredImageNet两个小样本学习基准数据集上进行了大量实验,验证提出方法的有效性。结果显示在miniImageNet数据集5-way 1-shot和5-way 5-shot设置上,提出的方法相比原型网络(prototypical networks)分类准确率分别提高1.9%和0.32%;在tieredImageNet数据集5-way 1-shot设置上,分类准确率相比原型网络提高0.33%。结论 提出基于类别语义相似性监督的小样本图像识别模型,提高小样本学习方法的泛化能力,提高小样本图像识别的准确率。 相似文献
2.
在标签均衡分布且标注样本足够多的数据集上,监督式分类算法通常可以取得比较好的分类效果。然而,在实际应用中样本的标签分布通常是不均衡的,分类算法的分类性能就变得比较差。为此,结合SLDA(Supervised LDA)有监督主题模型,提出一种不均衡文本分类新算法ITC-SLDA(Imbalanced Text Categorization based on Supervised LDA)。基于SLDA主题模型,建立主题与稀少类别之间的精确映射,以提高少数类的分类精度。利用SLDA模型对未标注样本进行标注,提出一种新的未标注样本的置信度计算方法,以及类别约束的采样策略,旨在有效采样未标注样本,最终降低不均衡文本的倾斜度,提升不均衡文本的分类性能。实验结果表明,所提方法能明显提高不均衡文本分类任务中的Macro-F1和G-mean值。 相似文献
3.
少样本文本分类中,原型网络对语义利用不足、可迁移特征挖掘不够,导致模型泛化能力不强,在新任务空间中分类性能不佳。从模型结构、编码网络、度量网络等角度提高模型泛化性,提出多任务原型网络(multiple-task prototypical network, MTPN)。结构上,基于原型网络度量任务增加辅助分类任务约束训练目标,提高了模型的语义特征抽取能力,利用多任务联合训练,获得与辅助任务更相关的语义表示。针对编码网络,提出LF-Transformer编码器,使用层级注意力融合底层通用编码信息,提升特征的可迁移性。度量网络使用基于BiGRU的类原型生成器,使类原型更具代表性,距离度量更加准确。实验表明,MTPN在少样本文本情感分类任务中取得了91.62%的准确率,比现有最佳模型提升了3.5%以上;在新领域的情感评论中,基于五条参考样本,模型对查询样本可获得超过90%的分类准确率。 相似文献
4.
针对基于孪生网络的小样本调制识别算法存在相似识别类别混淆的问题,提出一种基于网络度量的三分支孪生网络调制识别算法。通过三分支孪生神经网络(Triplet Siamese Neural Network,TSN)将输入三元样本组的原始特征映射至特征子空间中。将正负样本与参考样本特征并联输入至两个参数共享的关系网络(Relation Network,RN),学习一个非线性的度量函数。通过各个类别的特征向量生成各类别的类原型,作为测试过程中的类特征输入。为降低信道噪声和信号接收误差对均值类原型表达的影响,采用局部异常因子算法(Local Outlier Factor,LOF)剔除类别中偏差数据。在公开的调制数据集DeepSig中进行验证,仿真结果表明,TSN-RN-LOF算法模型可以充分利用相似类别之间的差异信息,提取更具辨识度的特征,取得更优的识别性能。 相似文献
5.
小样本关系抽取任务是自然语言处理中的热点问题,旨在使用低成本的标注数据训练关系抽取模型。目前广泛使用的原型网络存在类原型表达不准确、不完整等问题。为了克服该问题,提出一种自适应胶囊网络(adaptive capsule network,ACNet),ACNet借助胶囊网络的归纳能力生成类原型,并在此基础上对动态路由过程进行评估,使其面对不同样本能自适应调整网络参数。同时,在ACNet中引入一种记忆迭代机制,帮助模型快速确定类表示。在小样本关系数据集FewRel上进行实验验证得出,ACNet能够有效处理小样本关系抽取任务。 相似文献
6.
目前实体关系提取大都使用卷积神经网络(CNN)和循环神经网络(RNN)。但CNN和RNN均以标量形式进行特征表达,对位置信息的敏感度不够理想。同时,CNN和RNN的最大池化(max-pooling)导致特征信息丢失。针对这两个问题,引入胶囊网络(CapsuleNet),构建了具备位置感知能力的Position Perception CapsuleNet(PPCNet)。胶囊(Capsule)是一组神经元,特征表达基于向量形式。PPCNet将词间的位置关系转化为位置向量(position embedding)融入Capsule以获得位置感知能力。此外,PPCNet使用动态路由(Dynamic routing)替代池化,以减少特征损失,在SemEval-2010task8数据集上得到82.84%的F1值。 相似文献
7.
3D点云语义分割在自动驾驶等现实应用中起着重要作用。现有大部分点云语义分割方法均依赖于大量获取成本昂贵的点级标签用于全监督训练,且在推理时无法扩展到对不可见新类的识别上。为克服上述限制,少样本学习(few-shot learning)通过仅使用少量标注的新类样本来实现到新知识的泛化。在对原型网络(prototypical network)研究基础上,设计一种对点云视觉原型进行自对齐、跨对齐正则化,并进一步矫正优化的少样本3D点云语义分割框架,以充分利用支撑集信息。在公开数据集S3DIS和ScanNet上不同少样本设置下(N-way,K-shot)的实验充分证明了方法在分割效果和推理效率上的优越性。 相似文献
8.
目的 针对点云分割需要大量监督信息所造成的时间成本高、计算效率低的问题,采用融合原型对齐的小样本元学习算法对点云进行语义分割,使模型能够在监督信息很少的情况下完成分割任务。方法 首先,为了避免小样本训练时易导致的过拟合问题,采用2个边缘卷积层(edge convolution layer,EdgeConv)与6个MLP (multilayer perceptron)交叉构造DGCNN (dynamic graph convolutional neural network),同时还保证了能充分学习到点云信息;然后,以N-way K-shot的形式将数据集输入上述网络学习支持集与查询集的特征,通过average pooling feature获取类别原型并融合原型对齐算法得到更为鲁棒的支持集原型;最后,通过计算查询集点云特征与支持集原型的欧氏距离实现点云分割。结果 在S3DIS (Stanford large-scale 3D indoor spaces dataset)、ScanNet和闽南古建筑数据集上进行点云语义分割实验,与原型网络和匹配网络在S3DIS数据集上进行比较。分割1-way时,平均交并比(mean intersection over union,mIoU)相比原型网络和匹配网络分别提高了0.06和0.33,最高类别的mIoU达到0.95;分割2-way时,mIoU相比原型网络提高了0.04;将DGCNN网络与PointNet++做特征提取器的对比时,分割ceiling和floor的mIoU分别提高了0.05和0.30。方法应用在ScanNet数据集和闽南古建筑数据集上的分割mIoU分别为0.63和0.51。结论 提出的方法可以在少量标记数据的情况下取得良好的点云分割效果。相比于此前需用大量标记数据所训练的模型而言,只需要很少的监督信息,便能够分割出该新类,提高了模型的泛化能力。当面临样本的标记数据难以获得的情况时,提出的方法更能够发挥关键作用。 相似文献
9.
针对浅层的单模型文本分类算法不能很好地提取到文本序列多层次特征的问题,提出一种transformer-capsule集成模型,分别利用胶囊网络(capsule network)和transformer来提取文本的局部短语特征和全局语义特征,通过集成的形式更全面地得到文本序列的多层次特征表示。此外,针对传统胶囊网络动态路由时存在部分噪音胶囊干扰的问题,提出基于注意力机制的动态路由算法,赋给噪音胶囊较小的权重,减少传递给后续胶囊的干扰信息,实验证明该机制能有效提高分类性能。选取文本分类通用语料库中4个单标签数据集和1个多标签Reuters-21578数据集进行实验,取得了较好的实验结果,其中在Reuters-21578上F1值相比Capsule-B模型提升了3.6%,达到了89.4%。 相似文献
10.
针对步态识别在反恐、安防领域亟待解决的小样本问题,提出了一种基于深度卷积神经网络(convolutional and neural network,CNN)和DLTL(dual learning and transfer learning)的步态虚拟样本生成方法。首先用基于VGG19的深度卷积神经网络模型低层响应提取步态风格特征图,然后利用基于对抗网络的对偶学习(dual learning,DL)对风格特征图进行风格训练,得到风格特征模型;其次利用VGG19模型的高层响应提取步态内容特征图,然后让步态内容特征图对风格特征模型中的风格特征进行学习;最后使用迁移学习TL(transfer learning)获得步态虚拟偏移样本。实验结果表明,经过DLTL风格学习生成的步态虚拟样本虽然整体风格发生改变,但人体步态特征没有改变,可有效扩充小样本容量;当虚拟样本增加到一定数量时,步态识别率有所提升。该方法与现有步态虚拟样本生成方法进行对比实验,结果表明该算法优于现有方法,能够大量生成虚拟样本且稳定提高步态识别的识别率。 相似文献
11.
S. Shaw 《Journal of Computer Assisted Learning》1993,9(2):93-99
Abstract This paper describes an approach to the design of interactive multimedia materials being developed in a European Community project. The developmental process is seen as a dialogue between technologists and teachers. This dialogue is often problematic because of the differences in training, experience and culture between them. Conditions needed for fruitful dialogue are described and the generic model for learning design used in the project is explained. 相似文献
12.
European Community policy and the market 总被引:1,自引:0,他引:1
C. Lloyd 《Journal of Computer Assisted Learning》1993,9(2):86-91
Abstract This paper starts with some reflections on the policy considerations and priorities which are shaping European Commission (EC) research programmes. Then it attempts to position the current projects which seek to capitalise on information and communications technologies for learning in relation to these priorities and the apparent realities of the marketplace. It concludes that while there are grounds to be optimistic about the contribution EC programmes can make to the efficiency and standard of education and training, they are still too technology driven. 相似文献
13.
融合集成方法已经广泛应用在模式识别领域,然而一些基分类器实时性能稳定性较差,导致多分类器融合性能差,针对上述问题本文提出了一种新的基于多分类器的子融合集成分类器系统。该方法考虑在度量层融合层次之上通过对各类基多分类器进行动态选择,票数最多的类别作为融合系统中对特征向量识别的类别,构成一种新的自适应子融合集成分类器方法。实验表明,该方法比传统的分类器以及分类融合方法识别准确率明显更高,具有更好的鲁棒性。 相似文献
14.
Wayne O’Brien Author Vitae 《Journal of Systems and Software》2008,81(11):1997-2013
Development of software intensive systems (systems) in practice involves a series of self-contained phases for the lifecycle of a system. Semantic and temporal gaps, which occur among phases and among developer disciplines within and across phases, hinder the ongoing development of a system because of the interdependencies among phases and among disciplines. Such gaps are magnified among systems that are developed at different times by different development teams, which may limit reuse of artifacts of systems development and interoperability among the systems. This article discusses such gaps and a systems development process for avoiding them. 相似文献
15.
This paper presents control charts models and the necessary simulation software for the location of economic values of the control parameters. The simulation program is written in FORTRAN, requires only 10K of main storage, and can run on most mini and micro computers. Two models are presented - one describes the process when it is operating at full capacity and the other when the process is operating under capacity. The models allow the product quality to deteriorate to a further level before an existing out-of-control state is detected, and they can also be used in situations where no prior knowledge exists of the out-of-control causes and the resulting proportion defectives. 相似文献
16.
Going through a few examples of robot artists who are recognized worldwide, we try to analyze the deepest meaning of what
is called “robot art” and the related art field definition. We also try to highlight its well-marked borders, such as kinetic
sculptures, kinetic art, cyber art, and cyberpunk. A brief excursion into the importance of the context, the message, and
its semiotics is also provided, case by case, together with a few hints on the history of this discipline in the light of
an artistic perspective. Therefore, the aim of this article is to try to summarize the main characteristics that might classify
robot art as a unique and innovative discipline, and to track down some of the principles by which a robotic artifact can
or cannot be considered an art piece in terms of social, cultural, and strictly artistic interest.
This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January
31–February 2, 2008 相似文献
17.
David Poole 《Computational Intelligence》1989,5(2):97-110
Although there are many arguments that logic is an appropriate tool for artificial intelligence, there has been a perceived problem with the monotonicity of classical logic. This paper elaborates on the idea that reasoning should be viewed as theory formation where logic tells us the consequences of our assumptions. The two activities of predicting what is expected to be true and explaining observations are considered in a simple theory formation framework. Properties of each activity are discussed, along with a number of proposals as to what should be predicted or accepted as reasonable explanations. An architecture is proposed to combine explanation and prediction into one coherent framework. Algorithms used to implement the system as well as examples from a running implementation are given. 相似文献
18.
Watts S. Humphrey 《Annals of Software Engineering》2002,14(1-4):39-72
This paper provides the author's personal views and perspectives on software process improvement. Starting with his first work on technology assessment in IBM over 20 years ago, Watts Humphrey describes the process improvement work he has been directly involved in. This includes the development of the early process assessment methods, the original design of the CMM, and the introduction of the Personal Software Process (PSP)SM and Team Software Process (TSP){SM}. In addition to describing the original motivation for this work, the author also reviews many of the problems he and his associates encountered and why they solved them the way they did. He also comments on the outstanding issues and likely directions for future work. Finally, this work has built on the experiences and contributions of many people. Mr. Humphrey only describes work that he was personally involved in and he names many of the key contributors. However, so many people have been involved in this work that a full list of the important participants would be impractical. 相似文献
19.
基于复小波噪声方差显著修正的SAR图像去噪 总被引:4,自引:1,他引:3
提出了一种基于复小波域统计建模与噪声方差估计显著性修正相结合的合成孔径雷达(Synthetic Aperture Radar,SAR)图像斑点噪声滤波方法。该方法首先通过对数变换将乘性噪声模型转化为加性噪声模型,然后对变换后的图像进行双树复小波变换(Dualtree Complex Wavelet Transform,DCWT),并对复数小波系数的统计分布进行建模。在此先验分布的基础上,通过运用贝叶斯估计方法从含噪系数中恢复原始系数,达到滤除噪声的目的。实验结果表明该方法在去除噪声的同时保留了图像的细节信息,取得了很好的降噪效果。 相似文献
20.
R. NOSS 《Journal of Computer Assisted Learning》1987,3(1):2-12
Abstract This paper considers some results of a study designed to investigate the kinds of mathematical activity undertaken by children (aged between 8 and 11) as they learned to program in LOGO. A model of learning modes is proposed, which attempts to describe the ways in which children used and acquired understanding of the programming/mathematical concepts involved. The remainder of the paper is concerned with discussing the validity and limitations of the model, and its implications for further research and curriculum development. 相似文献