基于距离测度学习的AP聚类图像标注

针对有效利用图像底层视觉特征和图像语义特征进行图像标注,提出一种改进的AP（Affinity Propagation）聚类标注模型。首先采用半监督距离测度学习算法,融合图像语义信息,训练得到新的距离测度。然后使用新的距离测度对每一类图像进行AP聚类,生成各类图像的聚类中心,计算待标注图像到各类图像聚类中心的平均距离,确定待标注图像类别。最后计算待标注图像到类内各个聚类中心的距离,确定待标注图像类内类别,统计该类别下图像的标注词,作为待标注图像的标注词。在Corel5K和NUS-WIDE数据集上进行了实验,经验证,该方法有效提高了标注精度。     

基于可判别超平面树的生成模型图像标注方法

图像语义的自动标注是一个具有挑战性的研究课题,目前常见的机器学习方法,如统计生成模型(generative model)与判别模型(discriminative model)都被用于该问题的研究中.然而由于语义鸿沟的存在、图像训练数据的不平衡性以及图像标注的多标签特性等问题,使得上述方法的性能都有待进一步提高.提出一种基于可判别超平面树的生成模型图像标注方法.该方法根据待标注目标图像的高生成概率邻域,建立局部超平面分类树,进而利用同层类间可判别信息,按自顶向下的层次分类得到待标注图像的语义相关图像集合.由此得到的相关类信息与新的生成模型框架相结合对待标注图像与语义关键词的联合概率进行估计,实现对目标图像的标注.其特点在于生成模型与判别模型方法得到了有效结合,可判别超平面树对隐含语义聚类的判别分析是对待标注图像的生成"邻域"的逐步求精过程,有效地提高了生成模型标注准确度;而对于判别分析难以解决的多标签分类、训练数据不平衡等问题,此方法通过联合概率估计自然地实现目标图像的多标签分配.在常用的包含5 000幅图像的ECCV2002数据集进行了实验,结果表明,与目前已知的具有较好标注效果的基于生成模型的MBRM模型(采用图像分割方法)以及基于辨别分析的ASVM-MIL相比,此方法的F1因子分别提高了14%和13%.     

基于未知类语义约束自编码的零样本图像分类

为缓解传统零样本图像分类模型中存在的领域偏移问题,提出一种基于未知类语义约束自编码的零样本图像分类模型.首先,利用预训练的ResNet101网络提取所有已知类和未知类图像的视觉特征;其次,通过编码器将提取的图像深度视觉特征从视觉空间映射到语义空间;然后,通过解码器将映射后得到的语义向量重构为视觉特征向量,在语义自编码器的训练过程中,利用未知类图像的聚类视觉中心和未知类语义类原型的分布对齐施加约束,以缓解领域偏移问题;最后,基于经编码器预测得到的测试图像语义向量和各测试类语义类原型之间的相似性,采用最近邻算法实现零样本图像分类.在AwA2和CUB数据集上的实验结果表明,所提出模型具有较高的分类准确度.     

基于形式概念分析的图像场景语义标注模型

为生成有效表示图像场景语义的视觉词典,提高场景语义标注性能,提出一种基于形式概念分析(FCA)的图像场景语义标注模型。该方法首先将训练图像集与其初始的视觉词典抽象为形式背景,采用信息熵标识了各视觉单词的权重,并分别构造了各场景类别概念格结构;然后再利用各视觉单词权重的均值刻画概念格内涵上各组合视觉单词标注图像的贡献,按照类别视觉词典生成阈值,从格结构上有效提取了标注各类场景图像语义的视觉词典;最后,利用K最近邻标注测试图像的场景语义。在Fei-Fei Scene 13类自然场景图像数据集上进行实验,并与Fei-Fei方法和Bai方法相比,结果表明该方法在β=0.05和γ=15时,标注分类精度更优。     

基于对比学习的超多类深度图像聚类模型

图像聚类通过表征学习对图像数据降维并提取有效特征而后进行聚类分析。当图像数据存在超多类别时,数据分布的复杂性和类簇的密集性严重影响了现有方法的实用性。为此,提出了基于对比学习的超多类深度图像聚类模型,主要分为3个阶段：首先,改进对比学习方法训练特征模型以使类簇分布均匀;其次,基于语义相似性原则多视角挖掘实例语义最近邻信息;最后,将实例及其最近邻作为自监督信息训练聚类模型。根据实验类型的不同,设计了消融实验和对比实验。在消融实验中,证明了所提方法使类簇均匀分布在映射空间,并可靠挖掘语义最近邻信息。在对比实验中,将其与先进算法在7个基准数据集上进行了比较,在ImageNet-200类数据集上,其准确率比目前先进方法提升了10.6%;在ImageNet-1000类数据集上,其准确率比目前先进算法提升了9.2%。     

基于互信息约束聚类的图像语义标注

提出一种基于互信息约束聚类的图像标注算法。采用语义约束对信息瓶颈算法进行改进,并用改进的信息瓶颈算法对分割后的图像区域进行聚类,建立图像语义概念和聚类区域之间的相互关系;对未标注的图像,提出一种计算语义概念的条件概率的方法,同时考虑训练图像的先验知识和区域的低层特征,最后使用条件概率最大的语义关键字对图像区域语义自动标注。对一个包含500幅图像的图像库进行实验,结果表明,该方法比其他方法更有效。     

集成视觉特征和语义信息的相关反馈方法

为了有效地利用图像检索系统的语义分类信息和视觉特征,提出一种基于Bayes的集成视觉特征和语义信息的相关反馈检索方法.首先,将图像库的数据经语义监督的视觉特征聚类算法划分为小的聚类,每个聚类内数据的视觉特征相似并且语义类别相同;然后以聚类为单位标注正负反馈的实例,这显著区别于以单个图像为单位的相关反馈过程;最后分别以基于视觉特征的Bayes分类器和基于语义的Bayes分类器修正相似距离.在图像库上的实验表明,只用较少的反馈次数就可以达到较高的检索准确率.     

一种新的图像语义自动标注与检索算法*

提出了一种新的利用图像语义词汇表进行图像自动标注与检索的方法.采用混合层次模型在已标注好的训练图像集上计算图像区域类与关键字的联合概率分布,并用生成的模型标注未曾观察过的测试图像集,或用来进行基于语义的图像检索.实验结果表明,该方法在标注、检索精度和效率方面均优于当前其他方法.     

基于语义分类的文物图像标注研究

由于图像数据中普遍存在的“语义鸿沟”问题,传统的基于内容的图像检索技术对于数字图书馆中的图像检索往往力不从心。而图像标注能有效地弥补语义的缺失。文中分析了图像语义标注的现状以及存在的问题,提出了基于语义分类的文物语义标注方法。算法首先通过构建一个Bayes语义分类器对待标注图像进行语义分类,进而通过在语义类内部建立基于统计的标注模型,实现了图像的语义标注。在针对文物图像进行标注的实验中,该方法获得了较好的标注准确率和效率。     

基于IETM的图像类装备保障数据语义标注研究

为了有效的组织、查询和浏览海量的图像类装备保障数据,分析了现有图模型图像语义标注方法的弊端,选取了装备IETM内的图像类装备保障数据信息作为图像语义标注的样本数据,并结合TF*IDF权值理论,改进了图模型语义标注方法的语义标注词选定方法,构建了基于装备IETM的图像类装备保障数据语义标注模型。实验结果表明,所提出的图像类装备保障数据语义标注模型及算法能够有效地提升图像数据信息查询的查准率与查全率,能够在一定程度上满足用户对图像类装备保障数据语义标注的需求。     

一种适合弱标签数据集的图像语义标注方法

真实环境下数据集中广泛存在着标签噪声问题,数据集的弱标签性已严重阻碍了图像语义标注的实用化进程.针对弱标签数据集中的标签不准确、不完整和语义分布失衡现象,提出了一种适用于弱标签数据集的图像语义标注方法.首先,在视觉内容与标签语义的一致性约束、标签相关性约束和语义稀疏性约束下,通过直推式学习填充样本标签,构建样本的近似语义平衡邻域.鉴于邻域中存在噪声干扰,通过多标签语义嵌入的邻域最大边际学习获得距离测度和图像语义的一致性,使得近邻处于同一语义子空间.然后,以近邻为局部坐标基,通过邻域非负稀疏编码获得目标图像和近邻的部分相关性,并构建局部语义一致邻域.以邻域内的语义近邻为指导并结合语境相关信息,进行迭代式降噪与标签预测.实验结果表明了方法的有效性.     

Learning multi-task local metrics for image annotation

The goal of image annotation is to automatically assign a set of textual labels to an image to describe the visual contents thereof. Recently, with the rapid increase in the number of web images, nearest neighbor (NN) based methods have become more attractive and have shown exciting results for image annotation. One of the key challenges of these methods is to define an appropriate similarity measure between images for neighbor selection. Several distance metric learning (DML) algorithms derived from traditional image classification problems have been applied to annotation tasks. However, a fundamental limitation of applying DML to image annotation is that it learns a single global distance metric over the entire image collection and measures the distance between image pairs in the image-level. For multi-label annotation problems, it may be more reasonable to measure similarity of image pairs in the label-level. In this paper, we develop a novel label prediction scheme utilizing multiple label-specific local metrics for label-level similarity measure, and propose two different local metric learning methods in a multi-task learning (MTL) framework. Extensive experimental results on two challenging annotation datasets demonstrate that 1) utilizing multiple local distance metrics to learn label-level distances is superior to using a single global metric in label prediction, and 2) the proposed methods using the MTL framework to learn multiple local metrics simultaneously can model the commonalities of labels, thereby facilitating label prediction results to achieve state-of-the-art annotation performance.     

基于时空连续性的运动对象最近邻居查询

时空数据库中的运动对象最近邻居查询是NN Queries中的新问题，基于TPR-TREE索引结构的TP NN Queries算法能较好地处理对象的时态特性，但会多次查询同一对象。本文利用运动对象的时空连续性对TP NN Queries算法进行改进，通过一次查询TPR-TREE索引获取所有候选NN对象与查询对象的距离变化曲线，进而得到NN对象集，减少了查询及时空运算的次数。本文最后给出了实验分析。     

融合深度特征和语义邻域的自动图像标注*

传统图像标注方法中人工选取特征费时费力,传统标签传播算法忽视语义近邻,导致视觉相似而语义不相似,影响标注效果.针对上述问题,文中提出融合深度特征和语义邻域的自动图像标注方法.首先构建基于深度卷积神经网络的统一、自适应深度特征提取框架,然后对训练集划分语义组并建立待标注图像的邻域图像集,最后根据视觉距离计算邻域图像各标签的贡献值并排序得到标注关键词.在基准数据集上实验表明,相比传统人工综合特征,文中提出的深度特征维数更低,效果更好.文中方法改善传统视觉近邻标注方法中的视觉相似而语义不相似的问题,有效提升准确率和准确预测的标签总数.     

From classifiers to discriminators: A nearest neighbor rule induced discriminant analysis

The current discriminant analysis method design is generally independent of classifiers, thus the connection between discriminant analysis methods and classifiers is loose. This paper provides a way to design discriminant analysis methods that are bound with classifiers. We begin with a local mean based nearest neighbor (LM-NN) classifier and use its decision rule to supervise the design of a discriminator. Therefore, the derived discriminator, called local mean based nearest neighbor discriminant analysis (LM-NNDA), matches the LM-NN classifier optimally in theory. In contrast to that LM-NNDA is a NN classifier induced discriminant analysis method, we further show that the classical Fisher linear discriminant analysis (FLDA) is a minimum distance classifier (i.e. nearest Class-mean classifier) induced discriminant analysis method. The proposed LM-NNDA method is evaluated using the CENPARMI handwritten numeral database, the NUST603 handwritten Chinese character database, the ETH80 object category database and the FERET face image database. The experimental results demonstrate the performance advantage of LM-NNDA over other feature extraction methods with respect to the LM-NN (or NN) classifier.     

Dynamic time warping constraint learning for large margin nearest neighbor classification

Nearest neighbor (NN) classifier with dynamic time warping (DTW) is considered to be an effective method for time series classification. The performance of NN-DTW is dependent on the DTW constraints because the NN classifier is sensitive to the used distance function. For time series classification, the global path constraint of DTW is learned for optimization of the alignment of time series by maximizing the nearest neighbor hypothesis margin. In addition, a reduction technique is combined with a search process to condense the prototypes. The approach is implemented and tested on UCR datasets. Experimental results show the effectiveness of the proposed method.     

融合弱监督目标定位的细粒度小样本学习

目的 小样本学习旨在通过一幅或几幅图像来学习全新的类别。目前许多小样本学习方法基于图像的全局表征,可以很好地实现常规小样本图像分类任务。但是,细粒度图像分类需要依赖局部的图像特征,而基于全局表征的方法无法有效地获取图像的局部特征,导致很多小样本学习方法不能很好地处理细粒度小样本图像分类问题。为此,提出一种融合弱监督目标定位的细粒度小样本学习方法。方法 在数据量有限的情况下,目标定位是一个有效的方法,能直接提供最具区分性的区域。受此启发,提出了一个基于自注意力的互补定位模块来实现弱监督目标定位,生成筛选掩膜进行特征描述子的筛选。基于筛选的特征描述子,设计了一种语义对齐距离来度量图像最具区分性区域的相关性,进而完成细粒度小样本图像分类。结果 在miniImageNet数据集上,本文方法在1-shot和5-shot下的分类精度相较性能第2的方法高出0.56%和5.02%。在细粒度数据集Stanford Dogs和Stanford Cars数据集上,本文方法在1-shot和5-shot下的分类精度相较性能第2的方法分别提高了4.18%,7.49%和16.13,5.17%。在CUB 200-2011（Caltech-UCSD birds）数据集中,本文方法在5-shot下的分类精度相较性能第2的方法提升了1.82%。泛化性实验也显示出本文方法可以更好地同时处理常规小样本学习和细粒度小样本学习。此外,可视化结果显示出所提出的弱监督目标定位模块可以更完整地定位出目标。结论 融合弱监督目标定位的细粒度小样本学习方法显著提高了细粒度小样本图像分类的性能,而且可以同时处理常规的和细粒度的小样本图像分类。     

Image annotation refinement via 2P-KNN based group sparse reconstruction

Image annotation aims at predicting labels that can accurately describe the semantic information of images. In the past few years, many methods have been proposed to solve the image annotation problem. However, the predicted labels of the images by these methods are usually incomplete, insufficient and noisy, which is unsatisfactory. In this paper, we propose a new method denoted as 2PKNN-GSR (Group Sparse Reconstruction) for image annotation and label refinement. First, we get the predicted labels of the testing images using the traditional method, i.e., a two-step variant of the classical K-nearest neighbor algorithm, called 2PKNN. Then, according to the obtained labels, we divide the K nearest neighbors of an image in the training images into several groups. Finally, we utilize the group sparse reconstruction algorithm to refine the annotated label results which are obtained in the first step. Experimental results on three standard datasets, i.e., Corel 5K, IAPR TC12 and ESP Game, show the superior performance of the proposed method compared with the state-of-the-art methods.

     

Improving nearest neighbor classification with cam weighted distance

Nearest neighbor (NN) classification assumes locally constant class conditional probabilities, and suffers from bias in high dimensions with a small sample set. In this paper, we propose a novel cam weighted distance to ameliorate the curse of dimensionality. Different from the existing neighborhood-based methods which only analyze a small space emanating from the query sample, the proposed nearest neighbor classification using the cam weighted distance (CamNN) optimizes the distance measure based on the analysis of inter-prototype relationship. Our motivation comes from the observation that the prototypes are not isolated. Prototypes with different surroundings should have different effects in the classification. The proposed cam weighted distance is orientation and scale adaptive to take advantage of the relevant information of inter-prototype relationship, so that a better classification performance can be achieved. Experiments show that CamNN significantly outperforms one nearest neighbor classification (1-NN) and k-nearest neighbor classification (k-NN) in most benchmarks, while its computational complexity is comparable with that of 1-NN classification.     

Image attribute learning with ontology guided fused lasso

Extended from the traditional pure statistical learning methods, we propose to augment the statistical learning methods with ontology and apply this idea for image attribute learning. In order to capture structural information among attributes, the graph-guided fused lasso model is adopted and improved by a new distance metric based on WordNet. The novelty of our method is that we find the semantic correlation with the ontology-guided attribute space and integrate inter-attribute similarity information into the learning model. The hierarchy of ImageNet is exploited to define the image attributes and a dataset from ImageNet including over 30,000 images is collected. The experimental results show that this method can both improve the accuracy and accelerate the algorithm convergency. Moreover, the learned semantic correlation owns transfer ability to related applications.