Collaborative Research: Learning Taxonomies of the Visual World

合作研究：学习视觉世界的分类法

• 批准号: 0535278
• 负责人: Max Welling
• 金额: $ 13.93万
• 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: 2005
• 资助国家: 美国
• 起止时间: 2005-08-01 至 2009-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0535278&HistoricalAwards=false
• 关键词: Collaborative; Research; Learning; Taxonomies; Visual

Learning visual object categories, and recognizing objects in images, is perhaps the most difficult and exciting problem in machine vision today. In light of the fast growing data deluge in science, engineering, industry and society, recognition systems must be able to operate without human supervision. This poses new challenges: How can one learn automatically models of a large number of object classes from unlabelled images? How can one represent these object classes such that they can be searched efficiently? How can one leverage the learnt models to learn new object classes from very few examples?It is proposed that these challenges may be met by inferring hierarchical representations of object classes from unlabelled image data. Object classes are represented as constellations of parts, where each part extracts shape and appearance information.Non-parametric Bayesian techniques may be employed to organize these object classes into tree-structured representations. The richness of this representation grows incrementally as more data is presented to the system. New similarity measures between object classes naturally derive from this representation facilitating recognition.Outreach to the local community is established through a collaboration with the California State University Northridge where students, often minorities who are the first in the family to obtain a university degree, will have the opportunity to engage in visual recognition problems proposed by and relevant to local companies.

学习视觉对象类别和识别图像中的对象，可能是当今机器视觉中最困难和最令人兴奋的问题。鉴于科学、工程、工业和社会中数据的快速增长，识别系统必须能够在没有人类监督的情况下运行。这带来了新的挑战：如何从未标记的图像中自动学习大量对象类的模型？如何表示这些对象类，以便有效地搜索它们？如何利用学习的模型从很少的例子中学习新的对象类？有人建议，这些挑战可能会遇到的推断对象类的分层表示从未标记的图像数据。对象类被表示为部件的星座，其中每个部件提取形状和外观信息。非参数贝叶斯技术可以用于将这些对象类组织成树结构表示。这种表示的丰富性随着向系统呈现更多数据而递增。对象类之间的新的相似性措施自然来自这种表示促进recognition.Outreach到当地社区是通过与加州州立大学北岭的学生，往往是少数民族谁是第一个在家庭中获得大学学位的合作，将有机会从事视觉识别问题提出的，并与当地公司。