半监督多视图学习在大数据分析中的应用探讨

半监督多视图学习是机器学习领域一种极具潜力的大数据处理和分析方法,该方法能有效处理异构和半监督数据,并能方便地在线化和并行化,适合处理海量数据。该方法在大数据时代的应用前景值得研究人员和业界关注。指出未来需要通过引入其他领域新的研究技术和成果,不断丰富和完善半监督多视图学习的理论体系和算法设计,并在实验和实践中不断检验和探索。     

Ubiquitously Supervised Subspace Learning

In this paper, our contributions to the subspace learning problem are two-fold. We first justify that most popular subspace learning algorithms, unsupervised or supervised, can be unitedly explained as instances of a ubiquitously supervised prototype. They all essentially minimize the intraclass compactness and at the same time maximize the interclass separability, yet with specialized labeling approaches, such as ground truth, self-labeling, neighborhood propagation, and local subspace approximation. Then, enlightened by this ubiquitously supervised philosophy, we present two categories of novel algorithms for subspace learning, namely, misalignment-robust and semi-supervised subspace learning. The first category is tailored to computer vision applications for improving algorithmic robustness to image misalignments, including image translation, rotation and scaling. The second category naturally integrates the label information from both ground truth and other approaches for unsupervised algorithms. Extensive face recognition experiments on the CMU PIE and FRGC ver1.0 databases demonstrate that the misalignment-robust version algorithms consistently bring encouraging accuracy improvements over the counterparts without considering image misalignments, and also show the advantages of semi-supervised subspace learning over only supervised or unsupervised scheme.     

一种自动抑制离群点的子空间学习方法

子空间学习如主成分分析是有效的数据降维方法。但这类方法计算的基向量受离群(outlier)数据的影响很大,导致降维后的数据不能准确地刻画数据的真实分布。为了减少离群数据的影响,该文提出了一种改进的子空间学习方法。该方法不需要直接探测离群数据的位置,而且子空间的求解可归结为特征值分解问题,具有全局最优解。仿真数据上的试验表明该方法是有效的。     

Semi-Supervised Learning Based on Manifold in BCI

Abstract-A Laplacian support vector machine （LapSVM） algorithm, a semi-supervised learning based on manifold, is introduced to brain-computer interface （BCI） to raise the classification precision and reduce the subjects＇ training complexity. The data are collected from three subjects in a three-task mental imagery experiment. LapSVM and transductive SVM （TSVM） are trained with a few labeled samples and a large number of unlabeled samples. The results confirm that LapSVM has a much better classification than TSVM.     

Graph-Based Semi-Supervised Learning and Spectral Kernel Design

In this paper, we consider a framework for semi-supervised learning using spectral decomposition-based unsupervised kernel design. We relate this approach to previously proposed semi-supervised learning methods on graphs. We examine various theoretical properties of such methods. In particular, we present learning bounds and derive optimal kernel representation by minimizing the bound. Based on the theoretical analysis, we are able to demonstrate why spectral kernel design based methods can improve the predictive performance. Empirical examples are included to illustrate the main consequences of our analysis.     

Automatic Image Annotation Using Semi-Supervised Multi-Instance Multi-Label Learning Algorithm

Automatic image annotation has emerged as an important research topic. From the perspective of machine learning, the annotation task fits both multiinstance and multi-label learning framework due to the fact that an image is composed of multiple regions, and is associated with multiple keywords as well. In this paper, we propose a novel Semi-supervised multi-instance multi-label （SSMIML） learning framework, which aims at taking full advantage of both labeled and unlabeled data to address the annotation problem. Specifically, a reinforced diverse density algorithm is applied firstly to select the Instance prototypes （IPs） with respect to a given keyword from both positive and unlabeled bags. Then, the selected IPs are modeled using the Gaussian mixture model （GMM） in order to reflect the semantic class density distribution. Furthermore, based on the class distribution for a keyword, both positive and unlabeled bags are redefined using a novel feature mapping strategy. Thus, each bag can be represented by one fixed-length feature vector so that the manifold-ranking algorithm can be used subsequently to propagate the corresponding label from positive bags to unlabeled bags directly. Experiments on the Corel data set show that the proposed method outperforms most existing image annotation algorithms.     

一种基于半监督学习的应用层流量分类方法

基于应用层的流量分类在用户行为识别、网络带宽管理等方面有着十分重要的应用.将机器学习应用到应用层流量分类问题中.首先提出了一种基于熵函数的组合式特征选择算法,提取了5种TCP连接的特征.针对监督学习中无法识别新流量类型的问题,提出了一种基于半监督学习的流量分类算法.实验结果表明,算法的检测率优于Kmeans方法.在少量标记样本的情况下,随着未标记样本数增加,算法的检测率在增加.     

Semi-Supervised Deep Learning for Multi-Tissue Segmentation from Multi-Contrast MRI

Journal of Signal Processing Systems - Segmentation of thigh tissues (muscle, fat, inter-muscular adipose tissue (IMAT), bone, and bone marrow) from magnetic resonance imaging (MRI) scans is useful...     

一种基于伪标签的半监督少样本学习模型

如何将带有大量标记数据的源域知识模型迁移至带有少量标记数据的目标域是少样本学习研究领域的热点问题.针对现有的少样本学习算法在源域数据与目标域数据的特征分布差异较大时存在的泛化能力较弱的问题,提出一种基于伪标签的半监督少样本学习模型FSLSS（Few-Shot Learning based on Semi-Supervised）.首先,利用pytorch深度学习框架建立一个关系型深度学习网络,并使用源域数据对网络进行预训练;然后,使用此网络对目标域数据进行分类预测,将分类概率最大的类标签作为数据的伪标签;最后,利用目标域的伪标签数据和源域的真实标签数据对网络进行混合训练,并重复伪标签标记与混合训练过程.实验结果表明,相对于现有主流少样本学习算法,FSLSS模型有更好的泛化能力及知识迁移效果.     

一种基于半监督学习的窄带雷达目标识别系统

半监督学习算法利用少量的标注样本与大量的未标注样本进行模式识别问题中的样本分布探索。针对常规雷达目标识别系统中,样本难以准确标注、模板库建立复杂以及建立过程漫长的问题,采用半监督学习算法以减少模板库的建设代价,并启用多核学习来进行目标特征的自动选择。基于窄带飞机目标分类识别的数据分析表明,与基于监督学习算法的常规识别系统相比,所提的目标识别系统能够获得更高的分类准确率。     

Semi-Supervised Few-Shot Learning Via Dependency Maximization and Instance Discriminant Analysis

Journal of Signal Processing Systems - We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of...     

基于增量张量子空间学习的自适应目标跟踪

 传统的基于子空间的跟踪方法易于丢失图像所固有的部分结构和邻域信息,从而降低了目标匹配和跟踪的精度.为此,本文提出了一种增量张量子空间学习算法,用于跟踪目标的建模与模型更新.同时,将该模型与贝叶斯推理相结合,提出一种自适应目标跟踪算法:新方法首先对跟踪目标的外观进行建模,然后利用贝叶斯推理获得目标外观状态参数的最优估计,最后利用最优估计的目标观测更新目标张量子空间.实验结果表明,由于保持了目标外观的结构信息,本文提出的自适应目标跟踪方法具有较强的鲁棒性,在跟踪目标在姿态变化、短时遮挡和光照变化等情况下均可有效地跟踪目标.     

基于局部行为搜索策略的半监督学习算法及其应用研究

近年来,半监督学习在模式识别和机器学习领域引起了广泛关注。在这些方法中,半监督支持向量机是非常主流的一类方法。然而,学习过程中热核函数的参数选择问题一直困扰着研究人员,若选取不当,学习性能会显著下降。为了解决该问题,本文提出一种新颖的基于局部行为搜索策略的半监督学习算法。新算法基于人类行为搜索策略,传统的支持向量机被正则化为拉普拉斯图。在搜索到特征空间的局部分布后,行为因子能够映射到样本邻域的潜在概率分布。为验证新算法有效性,本文分别进行了UCI数据集和实际通信辐射源特征数据集实验。实验结果显示与传统方法相比,新算法的分类结果能够更加有效和稳定。      

鲁棒自加权多核子空间图聚类算法

针对线性加权多核图聚类方法限制了共识核的表达能力和再生核希尔伯特空间中噪声污染的问题,提出一种鲁棒多核子空间图聚类算法(RSMKL),旨在增强核的表达能力和提高核空间中噪声的鲁棒性.该算法利用一种新颖的非线性自加权核融合策略来生成最佳的共识核,同时在核空间利用低秩约束模型来消除噪声对关系图质量的影响.最后,提出一种基于交替方向乘子的迭代优化算法求解目标函数.与5种同类流行算法在5个常用数据集上比较,实验结果表明RSMKL在聚类精度(ACC)、标准互信息(NMI)和聚类纯度(Purity)上具有更好的聚类性能.     

Image Denoising Via Sparse Dictionaries Constructed by Subspace Learning

In this paper, we propose a combinational algorithm for the removal of zero-mean white and homogeneous Gaussian additive noise from a given image. Image denoising is formulated as an optimization problem. This is iteratively solved by a weighted basis pursuit (BP) in the closed affine subspace. The patches extracted from a given noisy image can be sparsely and approximately represented by adaptively choosing a few nearest neighbors. The approximate reconstruction of these denoised patches is performed by the sparse representation on two dictionaries, which are built by a discrete cosine transform and the noisy patches, respectively. Experiments show that the proposed algorithm outperforms both BP denoising and Sparse K-SVD. This is because the underlying structure of natural images is better captured and preserved. The results are comparable to those of the block-matching 3D filtering algorithm.     

Recovery of Lost Speech Segments Using Incremental Subspace Learning

An incremental subspace learning scheme to recover lost speech segments online is presented. Our contributions in this work are twofold. First, the recovery problem is transformed into an interpolation problem of the time‐varying gains via nonnegative matrix factorization. Second, incremental nonnegative matrix factorization is employed to allow online processing and track the evolution of speech statistics. The effectiveness of the proposed scheme is confirmed by the experiment results.     

稀疏特征空间嵌入正则化：鲁棒的半监督学习框架

在机器学习领域,半监督学习作为一种有力工具吸引了越来越多的关注,其利用少量带标签数据和大量无标签数据进行有效学习,其中基于图的半监督学习方法因其优雅的数学形式和良好的学习性能而引起更广泛的研究。针对现有基于图的半监督学习方法所存在的模型参数敏感和数据判别信息不充分等问题,提出一种稀疏特征空间嵌入正则化（Sparse Feature Space embedding Regularization ,SFSR ）半监督学习框架,其主要思想为：首先分别将原始数据嵌入到线性特征空间,然后利用特征空间嵌入投影点集来稀疏重构原始数据,随后在由原始数据线性张成的标签空间通过保留这种稀疏表示关系来构建一个Laplacian正则化项,或称SFSR ,最后提出一个鲁棒的基于SFSR的半监督学习框架,在几个实际基准数据库上的综合实验结果证实了所提框架的鲁棒有效性。     

基于低秩表示的鲁棒判别特征子空间学习模型

特征子空间学习是图像识别及分类任务的关键技术之一,传统的特征子空间学习模型面临两个主要的问题。一方面是如何使样本在投影到特征空间后有效地保持其局部结构和判别性。另一方面是当样本含噪时传统学习模型所发生的失效问题。针对上述两个问题,该文提出一种基于低秩表示(LRR)的判别特征子空间学习模型,该模型的主要贡献包括：通过低秩表示探究样本的局部结构,并利用表示系数作为样本在投影空间的相似性约束,使投影子空间能够更好地保持样本的局部近邻关系;为提高模型的抗噪能力,构造了一种利用低秩重构样本的判别特征学习约束项,同时增强模型的判别性和鲁棒性;设计了一种基于交替优化技术的迭代数值求解方案来保证算法的收敛性。该文在多个视觉数据集上进行分类任务的对比实验,实验结果表明所提算法在分类准确度和鲁棒性方面均优于传统特征学习方法。