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 1307.7793cs.LGcs.AI
收藏

约束MAP推理的多维参数最小割

Multi-dimensional Parametric Mincuts for Constrained MAP Inference

Korea Advanced Institute of Science and Technology(韩国高等科学技术院);Microsoft Research Cambridge(微软研究院剑桥实验室)

Yongsub Lim, Kyomin Jung, Pushmeet Kohli

摘要:

在本文中,我们提出了新的算法推断的最大后验概率(MAP)解的离散成对随机场模型下的多个约束。我们展示了如何约束离散优化问题可以制定为一个多维参数mincut问题,通过其拉格朗日对偶,并证明我们的算法隔离的所有约束的情况下,该问题可以得到准确的解决。这些多个解决方案使我们甚至能够处理"软约束"(高阶罚函数)。此外,我们提出了两个实用的变种,我们的算法来解决问题的硬约束。我们还展示了我们的方法可以应用于解决各种约束离散优化问题,如子模块最小化和最短路径计算。使用前景-背景图像分割问题与统计约束的实验评估表明,我们的方法是更快,其结果是更接近地面真理标记相比,流行的连续松弛为基础的方法。

英文摘要:

In this paper, we propose novel algorithms for inferring the Maximum a Posteriori (MAP) solution of discrete pairwise random field models under multiple constraints. We show how this constrained discrete optimization problem can be formulated as a multi-dimensional parametric mincut problem via its Lagrangian dual, and prove that our algorithm isolates all constraint instances for which the problem can be solved exactly. These multiple solutions enable us to even deal with `soft constraints' (higher order penalty functions). Moreover, we propose two practical variants of our algorithm to solve problems with hard constraints. We also show how our method can be applied to solve various constrained discrete optimization problems such as submodular minimization and shortest path computation. Experimental evaluation using the foreground-background image segmentation problem with statistic constraints reveals that our method is faster and its results are closer to the ground truth labellings compared with the popular continuous relaxation based methods.

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。

↑