CIF: Medium:Collaborative Research: Nonasymptotic Analysis of Feature-Rich Decision Problems with Applications to Computer Vision

CIF：媒介：协作研究：特征丰富的决策问题的非渐近分析及其在计算机视觉中的应用

• 批准号: 1302438
• 负责人: Maxim Raginsky
• 金额: $ 66.92万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-07-01 至 2018-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1302438&HistoricalAwards=false
• 关键词: CIF; Medium; Collaborative; Research; Nonasymptotic

This project deals with theory and efficient algorithms for statistical decision problems that are radically different from those that have been studied to date in two key aspects: First, the decision-maker may choose among a large class of observation channels (features) of varying complexity and quality; and second, the total cost of computational resources that can be used prior to arriving at a decision is limited. Computer vision is a paradigmatic source of such feature-rich decision problems, requiring the use of multiple heterogeneous feature types, integration of diverse sources of contextual information, and possibly even human interaction.This project entails the development of a rigorous mathematical framework for feature-rich decision problems in accordance with three specific aims: (1) structural characterization of features as stochastic belief-refining filters; (2) universal cost-sensitive criteria for numerical comparison of features in terms of expected information gains; and (3) optimal value-of-information criteria for sequential feature selection that take into account both feature extraction costs and terminal decision losses. As corollaries, this research investigates connections to asymptotic information-theoretic characterizations of optimal feature selection rules and decisions. The fourth specific aim of the project is the development of practical algorithms for two challenging computer vision problems: active visual search and fine-grained categorization. This component of the project leverages theoretical aims (1) and (2) to develop practical cost- and loss-sensitive feature compression techniques. Theoretical aim (3) targets algorithms that function as autonomous decision-making agents. Faced with an inference task on an image, they apply cost-sensitive non-myopic value- of-information criteria to decide at each time step whether to extract a new feature from the image or to stop and declare an answer.

该项目涉及统计决策问题的理论和有效算法，这些算法与迄今为止在两个关键方面进行了研究的决策问题完全不同：首先，决策者可以选择各种复杂性和质量的大量观察渠道（功能）；其次，在做出决定之前可以使用的计算资源总成本是有限的。计算机视觉是这种范式丰富的决策问题的范式来源，需要使用多种异构特征类型，多样化的上下文信息来源的整合，甚至可能是人类互动。该项目需要开发一个严格的数学框架，以符合特征性的决策问题，以符合三个特定的目的：（1）结构性特征：（1）特征符合特征信念的结构性特征。 （2）根据预期信息获得的特征数值比较的通用成本敏感标准； （3）顺序特征选择的最佳信息标准，这些标准考虑了特征提取成本和终端决策损失。作为推论，这项研究调查了与最佳特征选择规则和决策的渐近信息理论特征的联系。该项目的第四个具体目的是开发两个具有挑战性的计算机视觉问题的实用算法：主动视觉搜索和细粒度分类。该项目的这个组成部分利用理论目标（1）和（2）来开发实用的成本和损失敏感特征压缩技术。理论目的（3）靶向充当自主决策代理的算法。面对图像上的推理任务，他们应用了具有成本敏感的非侧重值的信息标准，以决定是否从图像中提取新功能或停止并声明答案。