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

人类有能力学习他们所生活的世界日益复杂的表现形式。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)以30,000个对象类别的顺序进行识别。此外，人类不断地调整他们的世界模型，以响应数据。我们能在机器上复制这种终身学习的能力吗？在本项目中，PI构建数据流的分层表示。模型复杂性通过遵循非参数贝叶斯建模范例来适应数据中的新结构。特别是，我们的分层模型的深度和宽度会随着时间的推移而增长。此层次结构中的更深层次代表更抽象的概念，例如海滩场景？或者？椅子？，而较低的层次对应于部分，如一块沙子？或者？身体部位？这种分层结构的形成由图像的快速分层自下而上分割来指导。为了处理大量信息，PI跨多个CPU/GPU分布计算。他们开发了基于变分推理、内存受限在线推理、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的应用，从组织数字图书馆和万维网，建立视觉对象识别系统，成功地使用自主机器人和培训虚拟医生？通过处理来自世界各地的医院有关疾病、诊断和治疗的信息。结果通过科学出版物和公开可用的软件传播。

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.