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

RI：小型：协作研究：用于分层视觉分类的无限贝叶斯网络

• 批准号: 0914789
• 负责人: Pietro Perona
• 金额: $ 20万
• 依托单位: California Institute of Technology
• 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 2012-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0914789&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.

人类有能力学习他们所生活的世界的日益复杂的表征。在视觉领域，估计我们能够在多个粒度级别（例如脚趾甲、脚趾、腿、人体、人口）识别大约 30,000 个对象类别。此外，人类根据数据不断调整他们的世界模型。我们能否在机器中复制这种终生学习的能力？在这个项目中，PI 构建了数据流的分层表示。模型复杂性通过遵循非参数贝叶斯建模范例来适应新的数据结构。特别是，我们的分层模型的深度和宽度随着时间的推移而增长。该层次结构中的更深层次代表更抽象的概念，例如“海滩场景”或“椅子”，而较低的级别对应于零件，例如“一块沙子”？或“身体部分”。该层次结构的形成是由图像的快速分层自下而上分割引导的。为了处理大量信息，PI 将计算分布在许多 CPU/GPU 上。他们开发了基于变分推理、内存限制在线推理、并行采样和高效数据结构的新型快速推理技术。正在开发的技术具有大量潜在应用，包括组织数字图书馆和万维网、构建视觉对象识别系统、成功使用自主机器人以及培训“虚拟医生”。通过处理来自医院的有关疾病、诊断和治疗的全球信息。结果通过科学出版物和公开软件传播。