基于弱匹配概率典型相关性分析的图像自动标注

针对弱匹配多模态数据的相关性建模问题,提出了一种弱匹配概率典型相关性分析模型（semi-paired probabilistic CCA,简称SemiPCCA）.SemiPCCA模型关注于各模态内部的全局结构,模型参数的估计受到了未匹配样本的影响,而未匹配样本则揭示了各模态样本空间的全局结构.在人工弱匹配多模态数据集上的实验结果表明,SemiPCCA可以有效地解决传统CCA（canonical correlation analysis）和PCCA（probabilistic CCA）在匹配样本不足的情况下出现的过拟合问题,取得了较好的效果.提出了一种基于SemiPCCA的图像自动标注方法.该方法基于关联建模的思想,同时使用标注图像及其关键词和未标注图像学习视觉模态和文本模态之间的关联,从而能够更准确地对未知图像进行标注.     

基于局部流形重构的半监督多视图图像分类

为了在半监督情境下利用多视图特征中的信息提升分类性能,通过最小化输入特征向量的局部重构误差为以输入特征向量为顶点构建的图学习合适的边权重,将其用于半监督学习。通过将最小化输入特征向量的局部重构误差捕获到的输入数据的流形结构应用于半监督学习,有利于提升半监督学习中标签预测的准确性。对于训练样本图像的多视图特征的使用问题,借助于改进的典型相关分析技术学习更具鉴别性的多视图特征,将其有效融合并用于图像分类任务。实验结果表明,该方法能够在半监督情境下充分地挖掘训练样本的多视图特征表示的鉴别信息,有效地完成鉴别任务。     

Multi-view dimensionality reduction via canonical random correlation analysis

Canonical correlation analysis (CCA) is one of the most well-known methods to extract features from multi-view data and has attracted much attention in recent years. However, classical CCA is unsupervised and does not take discriminant information into account. In this paper, we add discriminant information into CCA by using random cross-view correlations between within-class samples and propose a new method for multi-view dimensionality reduction called canonical random correlation analysis (RCA). In RCA, two approaches for randomly generating cross-view correlation samples are developed on the basis of bootstrap technique. Furthermore, kernel RCA (KRCA) is proposed to extract nonlinear correlations between different views. Experiments on several multi-view data sets show the effectiveness of the proposed methods.     

Neighborhood Correlation Analysis for Semi-paired Two-View Data

Canonical correlation analysis (CCA) is a widely used technique for analyzing two datasets (two views of the same objects). However, CCA needs that the samples of the two views are fully-paired. Actually, we are often faced up with the semi-paired scenario where the number of available paired samples is limited and yet the number of unpaired samples is sufficient. For such a scenario, CCA is generally prone to overfitting and thus performs poorly, since its definition itself makes it only able to utilize those paired samples. To overcome such a shortcoming, several semi-paired variants of CCA have been proposed. However, unpaired samples in these methods are just used in the way of single-view leaning to capture individual views’ structure information for regularizing CCA. Intuitively, using unpaired samples in the way of two-view learning should be more natural and more attractive since CCA itself is a two-view learning method. As a result, a novel CCAs semi-paired variant named Neighborhood Correlation Analysis (NeCA), which uses unpaired samples in the two-view learning way, is developed through incorporating between-view neighborhood relationships into CCA. The relationships are acquired through leveraging within-view neighborhood relationships of each view’s all data (including paired and unpaired data) and between-view paired information. Thus, it can take more sufficient advantage of the unpaired samples and then mitigate overfitting effectively caused by the limited paired data. Promising experiments results on several popular multi-view datasets show its feasibility and effectiveness.     

基于半监督典型相关分析的多视图维数约简

为了有效地在半监督多视图情景下进行维数约简,提出了使用非负低秩图进行标签传播的半监督典型相关分析方法。非负低秩图捕获的全局线性近邻可以利用直接邻居和间接可达邻居的信息维持全局簇结构,同时,低秩的性质可以保持图的压缩表示。当无标签样本通过标签传播算法获得估计的标签信息后,在每个视图上构建软标签矩阵和概率类内散度矩阵。然后,通过最大化不同视图同类样本间相关性的同时最小化每个视图低维特征空间类内变化来提升特征鉴别能力。实验表明所提方法比已有相关方法能够取得更好的识别性能且更鲁棒。     

基于成对约束的判别型半监督聚类分析

现有一些典型的半监督聚类方法一方面难以有效地解决成对约束的违反问题,另一方面未能同时处理高维数据.通过提出一种基于成对约束的判别型半监督聚类分析方法来同时解决上述问题.该方法有效地利用了监督信息集成数据降维和聚类,即在投影空间中使用基于成对约束的K均值算法对数据聚类,再利用聚类结果选择投影空间.同时,该算法降低了基于约束的半监督聚类算法的计算复杂度,并解决了聚类过程中成对约束的违反问题.在一组真实数据集上的实验结果表明,与现有相关半监督聚类算法相比,新方法不仅能够处理高维数据,还有效地提高了聚类性能.     

基于多视图的半监督集成学习方法

针对集成学习方法中分类器差异性不足以及已标记样本少的问题,提出了一种新的半监督集成学习算法,将半监督方法引入到集成学习中,利用大量未标记样本的信息来细化每个基分类器,并且构造差异性更大的基分类器,首先通过多视图方法选取合适的未标记样本,并使用多视图方法将大量繁杂的特征属性分类,使用不同的特征降维方法对不同的视图进行降维...     

联合标签预测与判别投影学习的半监督典型相关分析

目的 典型相关分析是一种经典的多视图学习方法。为了提高投影方向的判别性能,现有典型相关分析方法通常采用引入样本标签信息的策略。然而,获取样本的标签信息需要付出大量的人力与物力,为此,提出了一种联合标签预测与判别投影学习的半监督典型相关分析算法。方法 将标签预测与模型构建相融合,具体地说,将标签预测融入典型相关分析框架中,利用联合学习框架学得的标签矩阵更新投影方向,进而学得的投影方向又重新更新标签矩阵。标签预测与投影方向的学习过程相互依赖、交替更新,预测标签不断地接近其真实标签,有利于学得最优的投影方向。结果 本文方法在AR、Extended Yale B、Multi-PIE和ORL这4个人脸数据集上分别进行实验。特征维度为20时,在AR、Extended Yale B、Multi-PIE和ORL人脸数据集上分别取得87%、55%、83%和85%识别率。取训练样本中每人2（3,4,5）幅人脸图像为监督样本,提出的方法识别率在4个人脸数据集上均高于其他方法。训练样本中每人5幅人脸图像为监督样本,在AR、Extended Yale B、Multi-PIE和ORL人脸数据集上分别取得94.67%、68%、83%和85%识别率。实验结果表明在训练样本标签信息较少情况下以及特征降维后的维数较低的情况下,联合学习模型使得降维后的数据最大限度地保存更加有效的信息,得到较好的识别结果。结论 本文提出的联合学习方法提高了学习的投影方向的判别性能,能够有效地处理少量的有标签样本和大量的无标签样本的情况以及解决两步学习策略的缺陷。     

A novel ensemble construction method for multi-view data using random cross-view correlation between within-class examples

Correlated information between multiple views can provide useful information for building robust classifiers. One way to extract correlated features from different views is using canonical correlation analysis (CCA). However, CCA is an unsupervised method and can not preserve discriminant information in feature extraction. In this paper, we first incorporate discriminant information into CCA by using random cross-view correlations between within-class examples. Because of the random property, we can construct a lot of feature extractors based on CCA and random correlation. So furthermore, we fuse those feature extractors and propose a novel method called random correlation ensemble (RCE) for multi-view ensemble learning. We compare RCE with existing multi-view feature extraction methods including CCA and discriminant CCA (DCCA) which use all cross-view correlations between within-class examples, as well as the trivial ensembles of CCA and DCCA which adopt standard bagging and boosting strategies for ensemble learning. Experimental results on several multi-view data sets validate the effectiveness of the proposed method.     

Semi-supervised orthogonal discriminant analysis via label propagation

Trace ratio is a natural criterion in discriminant analysis as it directly connects to the Euclidean distances between training data points. This criterion is re-analyzed in this paper and a fast algorithm is developed to find the global optimum for the orthogonal constrained trace ratio problem. Based on this problem, we propose a novel semi-supervised orthogonal discriminant analysis via label propagation. Differing from the existing semi-supervised dimensionality reduction algorithms, our algorithm propagates the label information from the labeled data to the unlabeled data through a specially designed label propagation, and thus the distribution of the unlabeled data can be explored more effectively to learn a better subspace. Extensive experiments on toy examples and real-world applications verify the effectiveness of our algorithm, and demonstrate much improvement over the state-of-the-art algorithms.     

Co-metric: a metric learning algorithm for data with multiple views

We address the problem of metric learning for multi-view data. Many metric learning algorithms have been proposed, most of them focus just on single view circumstances, and only a few deal with multi-view data. In this paper, motivated by the co-training framework, we propose an algorithm-independent framework, named co-metric, to learn Mahalanobis metrics in multi-view settings. In its implementation, an off-the-shelf single-view metric learning algorithm is used to learn metrics in individual views of a few labeled examples. Then the most confidently-labeled examples chosen from the unlabeled set are used to guide the metric learning in the next loop. This procedure is repeated until some stop criteria are met. The framework can accommodate most existing metric learning algorithms whether types-of-side-information or example-labels are used. In addition it can naturally deal with semi-supervised circumstances under more than two views. Our comparative experiments demonstrate its competiveness and effectiveness.     

Semi-supervised local Fisher discriminant analysis for dimensionality reduction

When only a small number of labeled samples are available, supervised dimensionality reduction methods tend to perform poorly because of overfitting. In such cases, unlabeled samples could be useful in improving the performance. In this paper, we propose a semi-supervised dimensionality reduction method which preserves the global structure of unlabeled samples in addition to separating labeled samples in different classes from each other. The proposed method, which we call SEmi-supervised Local Fisher discriminant analysis (SELF), has an analytic form of the globally optimal solution and it can be computed based on eigen-decomposition. We show the usefulness of SELF through experiments with benchmark and real-world document classification datasets.     

Semi-supervised multi-view maximum entropy discrimination with expectation Laplacian regularization

Semi-supervised multi-view learning has attracted considerable attention and achieved great success in the machine learning field. This paper proposes a semi-supervised multi-view maximum entropy discrimination approach (SMVMED) with expectation Laplacian regularization for data classification. It takes advantage of the geometric information of the marginal distribution embedded in unlabeled data to construct a semi-supervised classifier. Different from existing methods using Laplacian regularization, we propose to use expectation Laplacian regularization for semi-supervised learning in probabilistic models. We give two implementations of SMVMED and provide their kernel variants. One of them can be relaxed and formulated as a quadratic programming problem that is solved easily. Therefore, for this implementation, we provided two versions which are approximate and exact ones. The experiments on one synthetic and multiple real-world data sets show that SMVMED demonstrates superior performance over semi-supervised single-view maximum entropy discrimination, MVMED and other state-of-the-art semi-supervised multi-view learning methods.     

半监督复杂结构数据降维方法

现有的一些典型半监督降维算法,往往在利用标记信息的同时却忽略了样本数据本身的流形特征,或者是对流形特征使用不当,导致算法性能表现不佳并且应用领域狭窄。针对上述问题提出了半监督复杂结构数据降维方法,同时保持样本数据的全局与局部的流形特征。通过设置适当的目标函数,使算法结果能有更广泛的应用场合,实验证明了算法的有效性。     

A unified framework for semi-supervised PU learning

Traditional supervised classifiers use only labeled data (features/label pairs) as the training set, while the unlabeled data is used as the testing set. In practice, it is often the case that the labeled data is hard to obtain and the unlabeled data contains the instances that belong to the predefined class but not the labeled data categories. This problem has been widely studied in recent years and the semi-supervised PU learning is an efficient solution to learn from positive and unlabeled examples. Among all the semi-supervised PU learning methods, it is hard to choose just one approach to fit all unlabeled data distribution. In this paper, a new framework is designed to integrate different semi-supervised PU learning algorithms in order to take advantage of existing methods. In essence, we propose an automatic KL-divergence learning method by utilizing the knowledge of unlabeled data distribution. Meanwhile, the experimental results show that (1) data distribution information is very helpful for the semi-supervised PU learning method; (2) the proposed framework can achieve higher precision when compared with the state-of-the-art method.     

基于权值的局部保持半监督降维算法*

针对现有的半监督降维算法没有考虑存在于数据集中的大量未标记信息,不能得到最好的降维效果的问题。本文提出了一种改进的基于权值的局部保持半监督降维算法。该算法在保持正、负约束信息的同时,还利用距离权值来保持数据集所在的局部结构,从而提高降维效果。在UCI数据集上的实验表明,该算法能够提高降维的效果,尤其是在数据分布特性不满足流形结构时,仍能得到较好的聚类结果。     

A New Dimensionality Reduction Method with Correlation Analysis and Universum Learning

Dimensionality reduction (DR) is an important and essential preprocessing step in machine learning, possibly using discriminative information, neighbor information or correlation information and resulting in different DR methods. In this work, we design novel DR methods that employ another form of information, i.e., the maximal contradiction on Universum data which belong to the same domain as the task at hand, but do not belong to any class of the training data. It has been found that classification and clustering algorithms achieve favorable improvements with the help of Universum data and such learning methods are referred as to Univesum learning. Two new dimensionality reduction methods are proposed, termed as Improved CCA (ICCA) and Improved DCCA (IDCCA) respectively, that can simultaneously exploit the training data and the Universum data. Both of them can be expressed by generalized eigenvalue problem and solved by eigenvalue computation. The experiments on both synthetic and real-world datasets are presented to show that the proposed DR methods can obtain better performance.     

基于多视图半监督学习的人体行为识别

由于人的行为在本质上的复杂性,单一行为特征视图缺乏全面分析人类行为的能力.文中提出基于多视图半监督学习的人体行为识别方法.首先,提出3种不同模态视图数据,用于表征人体动作,即基于RGB模态数据的傅立叶描述子特征视图、基于深度模态数据的时空兴趣点特征视图和基于关节模态数据的关节点投影分布特征视图.然后,使用多视图半监督学习框架建模,充分利用不同视图提供的互补信息,确保基于少量标记和大量未标记数据半监督学习取得更好的分类精度.最后,利用分类器级融合技术并结合3种视图的预测能力,同时有效解决未标记样本置信度评估问题.在公开的人体行为识别数据集上实验表明,采用多个动作特征视图融合的特征表示方法的判别力优于单个动作特征视图,取得有效的人体行为识别性能.     

子空间半监督Fisher判别分析

Fisher判别分析寻找一个使样本数据类间散度与样本数据类内散度比值最大的子空间, 是一种很流行的监督式特征降维方法. 标注样本数据所属的类别通常需要大量的人工, 消耗大量的时间, 付出昂贵的成本. 为了解决同时利用有类别信息的样本数据和没有类别信息的样本数据用于寻找降维子空间的问题, 我们提出了一种子空间半监督Fisher判别分析方法. 子空间半监督Fisher判别分析寻找这样一个子空间, 这个子空间即保留了从有类别信息的样本数据中学习的类别判别结构, 也保留了从有类别信息的样本数据和没有类别信息的样本数据中学习的样本结构信息. 我们还推导了基于核的子空间半监督Fisher判别分析方法. 通过人脸识别实验验证了本文算法的有效性.     

Fractional-Order Embedding Supervised Canonical Correlations Analysis with Applications to Feature Extraction and Recognition

Due to the noise disturbance and limited number of training samples, within-set and between-set sample covariance matrices in canonical correlations analysis (CCA) based methods usually deviate from the true ones. In this paper, we re-estimate the covariance matrices by embedding fractional order and incorporate the class label information. First, we illustrate the effectiveness of the fractional-order embedding model through theory analysis and experiments. Then, we quote fractional-order within-set and between-set scatter matrices, which can significantly reduce the deviation of sample covariance matrices. Finally, we incorporate the supervised information, novel generalized CCA and discriminative CCA are presented for multi-view dimensionality reduction and recognition, called fractional-order embedding generalized canonical correlations analysis and fractional-order embedding discriminative canonical correlations analysis. Extensive experimental results on various handwritten numeral, face and object recognition problems show that the proposed methods are very effective and obviously outperform the existing methods in terms of classification accuracy.