arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1104.2580cs.CVcs.CGcs.GRcs.LG
收藏

假设和界限:基于形状先验的N-D分割、姿态估计和分类的计算注意力机制

Hypothesize and Bound: A Computational Focus of Attention Mechanism for Simultaneous N-D Segmentation, Pose Estimation and Classification Using Shape Priors

Johns Hopkins University(约翰斯·霍普金斯大学);University of Göttingen(哥廷根大学)

Diego Rother, Simon Schütz, René Vidal

摘要:

鉴于许多智能系统可获得的视觉信息的带宽不断增加,赋予它们什么值得关注,什么可以安全地忽略的感觉变得至关重要。本文提出了一个通用的数学框架,有效地分配可用的计算资源,以处理与解决给定的感知问题相关的输入部分。通过这一点,我们的意思是找到假设H(即,世界的状态),最大化函数L(H),表示每个假设“解释”输入的程度。考虑到感觉输入的大带宽,针对每个假设H完全评估L(H)在计算上是不可行的(例如,因为这意味着检查大量像素)。为了解决这个问题,我们提出了一个数学框架,有两个关键因素。第一个是边界机制(BM),用于针对给定的计算预算计算L(H)的上下界。这些界限比L(H)本身的计算成本低得多,可以通过增加分配给假设的预算来随时改进,并且经常足以丢弃假设。为了计算这些界限,我们开发了一种新的理论的形状和形状先验。第二个要素是注意力机制(FoAM),用于选择接下来应该细化哪个假设的边界,目标是以最少的计算量丢弃非最佳假设。拟议框架:1)是非常有效的,因为大多数假设都是用最少的计算来丢弃的; 2)是可并行的; 3)保证找到全局最优假设;以及4)其运行时间取决于手头的问题,而不是输入的带宽。我们实例化的问题,同时估计类,姿势,和一个无噪声版本的2D形状在一个2D图像的建议框架。

英文摘要:

Given the ever increasing bandwidth of the visual information available to many intelligent systems, it is becoming essential to endow them with a sense of what is worthwhile their attention and what can be safely disregarded. This article presents a general mathematical framework to efficiently allocate the available computational resources to process the parts of the input that are relevant to solve a given perceptual problem. By this we mean to find the hypothesis H (i.e., the state of the world) that maximizes a function L(H), representing how well each hypothesis "explains" the input. Given the large bandwidth of the sensory input, fully evaluating L(H) for each hypothesis H is computationally infeasible (e.g., because it would imply checking a large number of pixels). To address this problem we propose a mathematical framework with two key ingredients. The first one is a Bounding Mechanism (BM) to compute lower and upper bounds of L(H), for a given computational budget. These bounds are much cheaper to compute than L(H) itself, can be refined at any time by increasing the budget allocated to a hypothesis, and are frequently enough to discard a hypothesis. To compute these bounds, we develop a novel theory of shapes and shape priors. The second ingredient is a Focus of Attention Mechanism (FoAM) to select which hypothesis' bounds should be refined next, with the goal of discarding non-optimal hypotheses with the least amount of computation. The proposed framework: 1) is very efficient since most hypotheses are discarded with minimal computation; 2) is parallelizable; 3) is guaranteed to find the globally optimal hypothesis; and 4) its running time depends on the problem at hand, not on the bandwidth of the input. We instantiate the proposed framework for the problem of simultaneously estimating the class, pose, and a noiseless version of a 2D shape in a 2D image.

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。

↑