Cut, Glue, & Cut: A Fast, Approximate Solver for Multicut Partitioning
Cut, Glue, & Cut: A Fast, Approximate Solver for Multicut Partitioning
复制标题
剪切、粘合、
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
F. Hamprecht
中科院分区：
文献类型：
--
作者：
T. Beier;Thorben Kröger;Jörg H. Kappes;U. Köthe;F. Hamprecht
近年来，无监督图像分割日益流行。从超像素分割开始，构造了一个边加权区域邻接图。在图的所有分割中，选择最符合给定图像证据的分割，如通过切割边权重之和来测量的。由于该问题是NP难的，我们提出了一种新的基于移动范型的近似求解器：首先，将图递归划分为小区域(割阶段)。然后，对于任意两个相邻区域，我们考虑对这两个区域定义可能的移动(粘合和切割阶段)的替代切割。对于平面问题，可以找到最优移动，而对于非平面问题，存在有效的近似。我们在已发布的和新的基准数据集上对我们的算法进行了评估，我们在这里提供了这些数据集。所提出的算法找到的分段，根据损失函数衡量，与精确求解器找到的全局最优解一样接近地面真实情况。它比现有的近似方法要快得多，这对大规模问题很重要。
Recently, unsupervised image segmentation has become increasingly popular. Starting from a superpixel segmentation, an edge-weighted region adjacency graph is constructed. Amongst all segmentations of the graph, the one which best conforms to the given image evidence, as measured by the sum of cut edge weights, is chosen. Since this problem is NP-hard, we propose a new approximate solver based on the move-making paradigm: first, the graph is recursively partitioned into small regions (cut phase). Then, for any two adjacent regions, we consider alternative cuts of these two regions defining possible moves (glue & cut phase). For planar problems, the optimal move can be found, whereas for non-planar problems, efficient approximations exist. We evaluate our algorithm on published and new benchmark datasets, which we make available here. The proposed algorithm finds segmentations that, as measured by a loss function, are as close to the ground-truth as the global optimum found by exact solvers. It does so significantly faster then existing approximate methods, which is important for large-scale problems.
通过多重切割进行高阶分割
DOI：
10.1016/j.cviu.2015.11.005
发表时间：
2016
期刊：
Comput. Vis. Image Underst.
影响因子：
--
作者：
Kappes;M. Speth;G. Reinelt;C. Schnörr
通讯作者：
C. Schnörr