Learning With l1-Graph for Image Analysis
Learning With l1-Graph for Image Analysis
复制标题
DOI：
10.1109/tip.2009.2038764
复制
发表时间：
2010-04-01
影响因子：
10.6
通讯作者：
Huang, Thomas S.
中科院分区：
文献类型：
--
作者：
Cheng, Bin;Yang, Jianchao;Huang, Thomas S.
图的构造过程从本质上决定了这些面向图的图像分析学习算法的潜力。在本文中，我们提出了一个过程来建立所谓的有向图，其中的顶点涉及所有的样本和每个顶点的输入边的权重描述其规范驱动的重建从剩余的样本和噪声。然后，针对各种机器学习任务，提出了一系列新的算法.例如，在一个实施例中，数据聚类、子空间学习和半监督学习都是在图上导出的。与传统的最近邻图和ε球图相比，该图具有以下优点：1）对数据噪声具有更强的鲁棒性; 2）自动稀疏; 3）对单个数据具有自适应邻域。在三个真实数据集上的大量实验表明，图在数据聚类、子空间学习和半监督学习任务中的表现优于经典图。
The graph construction procedure essentially determines the potentials of those graph-oriented learning algorithms for image analysis. In this paper, we propose a process to build the so-called directed graph, in which the vertices involve all the samples and the ingoing edge weights to each vertex describe its norm driven reconstruction from the remaining samples and the noise. Then, a series of new algorithms for various machine learning tasks, e. g., data clustering, subspace learning, and semi-supervised learning, are derived upon the graphs. Compared with the conventional-nearest-neighbor graph and epsilon-ball graph, the graph possesses the advantages: 1) greater robustness to data noise, 2) automatic sparsity, and 3) adaptive neighborhood for individual datum. Extensive experiments on three real-world datasets show the consistent superiority of graph over those classic graphs in data clustering, subspace learning, and semi-supervised learning tasks.