Solving Minimum Cost Lifted Multicut Problems by Node Agglomeration

Solving Minimum Cost Lifted Multicut Problems by Node Agglomeration
复制标题

通过节点聚集解决最小成本提升的多割问题

DOI:
10.1007/978-3-030-20870-7_5
复制
发表时间:
2019
期刊:
影响因子:
--
通讯作者:
Margret Keuper
Margret Keuper
中科院分区:
--
文献类型:
--
作者:
Amirhossein Kardoost;Margret Keuper

文献摘要

参考文献

被引文献

相似文献

尽管其复杂性,最小成本提升的多割问题,近年来发现了广泛的应用,如图像和网格分解或多目标跟踪。它的解决方案是一个图分解成最佳数量的部分,优化w.r.t.在所述边集的超集上定义的成本函数。虽然目前可用的求解器为这个问题提供了高质量的解决方案方面的任务来解决,他们可以有更困难的问题实例的计算时间长。在这里,我们提出了两个变种的启发式求解器(原始可行启发式),greenhouse在有限的时间内生成的解决方案。对图像和网格分割基准的评估显示了这些解决方案的高质量。
Despite its complexity, the minimum cost lifted multicut problem has found a wide range of applications in recent years, such as image and mesh decomposition or multiple object tracking. Its solutions are decompositions of a graph into an optimal number of segments which are optimized w.r.t. a cost function defined on a superset of the edge set. While the currently available solvers for this problem provide high quality solutions in terms of the task to be solved, they can have long computation times for more difficult problem instances. Here, we propose two variants of a heuristic solver (primal feasible heuristic), which greedily generate solutions within a bounded amount of time. Evaluations on image and mesh segmentation benchmarks show the high quality of these solutions.
用于图像分割的快速平面相关聚类
DOI: 10.1007/978-3-642-33783-3_41
发表时间: 2012
影响因子: 2
作者:
Julian Yarkony;A. Ihler;Charless C. Fowlkes
通讯作者: Charless C. Fowlkes
使用扰动多重分割的概率相关聚类和图像分割
DOI: 10.1007/978-3-319-18461-6_19
发表时间: 2015
期刊:
影响因子: --
作者:
Kappes;P. Swoboda;B. Savchynskyy;T. Hazan;C. Schnörr
通讯作者: C. Schnörr
DOI: 10.1109/tpami.2011.280
发表时间: 2012-10
影响因子: 23.6
作者:
Amir Alush;J. Goldberger
通讯作者: Amir Alush;J. Goldberger
DOI: 10.1007/978-3-642-40395-8_20
发表时间: 2013
期刊: 2011 International Conference on Computer Vision
影响因子: --
作者:
Björn Andres;Julian Yarkony;B. S. Manjunath;Steffen Kirchhoff;Engin Türetken;Charless C. Fowlkes;H. Pfister
通讯作者: H. Pfister
DOI: 10.1109/iccv.2017.455
发表时间: 2017-04
期刊: 2017 IEEE International Conference on Computer Vision (ICCV)
影响因子: --
作者:
M. Keuper
通讯作者: M. Keuper