arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1004.4965stat.MLcs.CV
收藏

多对多图匹配:一种连续松弛方法

Many-to-Many Graph Matching: a Continuous Relaxation Approach

Mines ParisTech(巴黎高等矿业学院);Institut Curie(居里研究所);INSERM(法国国家健康与医学研究院);Ecole Normale Supérieure(巴黎高等师范学院)

Mikhail Zaslavskiy, Francis Bach, Jean-Philippe Vert

摘要:

图为各种计算机视觉应用中的对象表示提供了有效的工具。一旦构建了基于图的表示,一个重要的问题是如何比较图。这个问题通常被公式化为图匹配问题,其中人们寻求两个图的顶点之间的映射,该映射最佳地对齐它们的结构。在图匹配的经典公式中,仅考虑顶点之间的一对一对应。然而,在许多应用中,图不能完全匹配,更有趣的是考虑多对多的对应关系,其中一个图中的顶点簇与另一个图中的顶点簇匹配。在本文中,我们制定了多对多的图匹配问题作为一个离散的优化问题,并提出了一个近似算法的基础上连续松弛的组合问题。我们比较了我们的方法与其他现有的方法在几个基准计算机视觉数据集。

英文摘要:

Graphs provide an efficient tool for object representation in various computer vision applications. Once graph-based representations are constructed, an important question is how to compare graphs. This problem is often formulated as a graph matching problem where one seeks a mapping between vertices of two graphs which optimally aligns their structure. In the classical formulation of graph matching, only one-to-one correspondences between vertices are considered. However, in many applications, graphs cannot be matched perfectly and it is more interesting to consider many-to-many correspondences where clusters of vertices in one graph are matched to clusters of vertices in the other graph. In this paper, we formulate the many-to-many graph matching problem as a discrete optimization problem and propose an approximate algorithm based on a continuous relaxation of the combinatorial problem. We compare our method with other existing methods on several benchmark computer vision datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑