Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis

Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis
复制标题

学习扩散:设计用于可视化分析的偏微分方程的新视角

DOI:
10.1109/tpami.2016.2522415
复制
发表时间:
2016-12
影响因子:
23.6
通讯作者:
Luo Zhongxuan
Luo Zhongxuan
中科院分区:
计算机科学1区
文献类型:
--
作者:
Liu Risheng;Zhong Guangyu;Cao Junjie;Lin Zhouchen;Shan Shiguang;Luo Zhongxuan

文献摘要

参考文献

被引文献

相似文献

偏微分方程(PDEs)已用于制定图像处理几十年。一般来说,PDE系统由控制方程和边界条件两部分组成。在大多数以前的工作中,这两种方法通常都是由使用数学技能的人设计的。然而,在现实世界的可视化分析任务中,这种预定义的固定形式的pde可能无法描述可视化数据的复杂结构。更重要的是,很难将标记信息和判别分布先验纳入这些偏微分方程中。为了解决上述问题,我们提出了一个新的PDE框架,称为扩散学习(LTD),用于自适应地设计扩散PDE系统的控制方程和边界条件,用于不同类型的视觉数据上的各种视觉任务。据我们所知,本文所考虑的问题(即显著性检测和目标跟踪)以前从未被PDE模型解决过。在各种具有挑战性的基准数据库上的实验结果表明,对于所有测试的视觉分析任务,LTD优于现有的最先进的方法。
Partial differential equations (PDEs) have been used to formulate image processing for several decades. Generally, a PDE system consists of two components: the governing equation and the boundary condition. In most previous work, both of them are generally designed by people using mathematical skills. However, in real world visual analysis tasks, such predefined and fixed-form PDEs may not be able to describe the complex structure of the visual data. More importantly, it is hard to incorporate the labeling information and the discriminative distribution priors into these PDEs. To address above issues, we propose a new PDE framework, named learning to diffuse (LTD), to adaptively design the governing equation and the boundary condition of a diffusion PDE system for various vision tasks on different types of visual data. To our best knowledge, the problems considered in this paper (i.e., saliency detection and object tracking) have never been addressed by PDE models before. Experimental results on various challenging benchmark databases show the superiority of LTD against existing state-of-the-art methods for all the tested visual analysis tasks.
为计算机视觉设计智能偏微分方程:一种最优控制方法
DOI: 10.1016/j.imavis.2012.09.004
发表时间: 2011-09
影响因子: 4.7
作者:
Lin, Zhouchen;Zhang, Wei;Tang, Kewei;Su, Zhixun
通讯作者: Su, Zhixun
DOI: 10.1007/978-3-642-15549-9_9
发表时间: 2010-09
影响因子: 2.4
作者:
Risheng Liu;Zhouchen Lin;Wayne Zhang;Zhixun Su
通讯作者: Risheng Liu;Zhouchen Lin;Wayne Zhang;Zhixun Su
DOI: 10.1109/tpami.2011.272
发表时间: 2012-10-01
影响因子: 23.6
作者:
Goferman, Stas;Zelnik-Manor, Lihi;Tal, Ayellet
通讯作者: Tal, Ayellet
DOI: 10.1145/1201775.882269
发表时间: 2003-07
期刊: ACM SIGGRAPH 2003 Papers
影响因子: --
作者:
P. Pérez;Michel Gangnet;A. Blake
通讯作者: P. Pérez;Michel Gangnet;A. Blake
DOI: 10.1109/tip.2010.2069690
发表时间: 2010-12-01
影响因子: 10.6
作者:
Li, Chunming;Xu, Chenyang;Fox, Martin D.
通讯作者: Fox, Martin D.