RI:Small:Collaborative Research: Infinite Bayesian Networks for Hierarchical Visual Categorization

RI:Small:协作研究：用于分层视觉分类的无限贝叶斯网络

• 批准号: 0914783
• 负责人: Max Welling
• 金额: $ 30万
• 依托单位: University of California-Irvine
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-09-01 至 2014-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0914783&HistoricalAwards=false
• 关键词: RI; Small; Collaborative; Research; Infinite

Humans possess the ability to learn increasingly sophisticated representations of the world in which they live. In the visual domain, it is estimated that we are able to identify in the order of 30,000 object categories at multiple levels of granularity (e.g. toe-nail, toe, leg, human body, population). Moreover, humans continuously adapt their models of the world in response to data. Can we replicate this life-long-learning capacity in machines?In this project, the PIs build hierarchical representations of data streams. The model complexity adapts to new structure in data by following a nonparametric Bayesian modeling paradigm. In particular, the depth and width of our hierarchical models grow over time. Deeper layers in this hierarchy represent more abstract concepts, such as ?a beach scene? or ?chair?, while lower levels correspond to parts, such as a ?patch of sand? or ?body part?. The formation of this hierarchy is guided by fast hierarchical bottom up segmentation of the images.To process large amounts of information, the PIs distribute computation across many CPUs /GPUs. They develop novel fast inference techniques based on variational inference, memory bounded online inference, parallel sampling, and efficient data-structures.The technology under development has a large number of potential applications ranging from organizing digital libraries and the worldwide web, building visual object recognition systems, successfully employing autonomous robots and training a ?virtual doctor? by processing worldwide information from hospitals about diseases, diagnosis and treatments.Results are disseminated through scientific publications and publicly available software.

人类拥有学习他们所生活的世界日益复杂的表征的能力。在视觉领域，估计我们能够在多个粒度级别上识别30,000个对象类别（例如趾甲，脚趾，腿，人体，人口）。此外，人类不断根据数据调整他们的世界模型。我们能在机器上复制这种终身学习的能力吗？在这个项目中，pi构建数据流的分层表示。模型复杂度遵循非参数贝叶斯建模范式，适应数据中新的结构。特别是，我们的层次模型的深度和宽度随着时间的推移而增长。层次结构中的更深层表示更抽象的概念，例如？海滩场景？或椅子?，而较低的级别对应于部分，例如？一小块沙子？还是?身体部分?。这种层次结构的形成是由图像的快速分层自下而上分割指导的。为了处理大量的信息，pi将计算分布在许多cpu / gpu上。他们开发了基于变分推理、内存边界在线推理、并行采样和高效数据结构的新型快速推理技术。这项正在开发的技术有很多潜在的应用，从组织数字图书馆和全球网络，建立视觉对象识别系统，成功地使用自主机器人和训练人工智能。虚拟医生吗?通过处理来自世界各地医院的疾病、诊断和治疗信息。研究结果通过科学出版物和公开软件传播。