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

人类拥有学习他们所生活的世界的日益复杂的表征的能力。在视觉领域，据估计，我们能够在多个粒度级别（例如脚趾甲，脚趾，腿，人体，人口）上识别30，000个对象类别。此外，人类不断调整他们的世界模型以响应数据。我们能在机器中复制这种终身学习的能力吗？在这个项目中，PI构建数据流的层次表示。模型的复杂性通过遵循非参数贝叶斯建模范式来适应数据中的新结构。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。这个层次结构中更深的层表示更抽象的概念，比如？一个海滩的场景还是？椅子？而较低级别对应于部分，如a？一小块沙子？还是？身体的一部分？该层次结构的形成由图像的快速分层自底向上分割来引导。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快速推理技术。正在开发的技术有大量的潜在应用，从组织数字图书馆和万维网，建立视觉对象识别系统，成功地采用自主机器人和培训？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。研究结果通过科学出版物和公开软件传播。

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.