EAGER: Combining Knowledge with Data for Generalizable and Robust Visual Learning

EAGER：将知识与数据相结合，实现可推广且稳健的视觉学习

• 批准号: 1145152
• 负责人: Qiang Ji
• 金额: $ 20.24万
• 依托单位: Rensselaer Polytechnic Institute
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-10-01 至 2016-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1145152&HistoricalAwards=false
• 关键词: EAGER; Combining; Knowledge; Data; Generalizable

Computer vision has made tremendous progress in the past decades, partially enabled by the advanced machine learning techniques. But compared with human perception, computer vision remains primitive. One contributing factor for this is the data-driven nature of the current learning algorithms and their inability to incorporate any related knowledge. The data-driven methods tend to be database-specific and cannot generalize well to unseen data. This project addresses this issue through the introduction of a knowledge-augmented statistical learning framework. Within this framework, knowledge and data can be systematically exploited, captured, and are principally integrated to jointly train a vision algorithm. Developing such a framework, however, is challenging since the domain knowledge often exists in different and diverse formats, typically inaccessible to the data-driven statistical machine learning methods. To overcome this challenge, the research team systematically converts domain knowledge into either the constraints on the model or into pseudo-data, whereby they can be incorporated into the statistical learning methods. The project includes systematic identification of knowledge from different sources and concrete mechanisms to capture the knowledge and to convert them into formats easily accessible to the automatic machine learning methods. The project also involves demonstrating the effectiveness of the proposed framework for certain computer vision problems.The project provides the training for graduate and undergraduate students, and the research results are disseminated through publications and organization of the related workshops.

计算机视觉在过去几十年里取得了巨大的进步，部分原因是先进的机器学习技术。但与人类的感知相比，计算机视觉仍然很原始。造成这种情况的一个因素是当前学习算法的数据驱动性质，以及它们无法整合任何相关知识。数据驱动的方法往往是特定于数据库的，不能很好地泛化到不可见的数据。该项目通过引入知识增强的统计学习框架来解决这一问题。在这个框架内，知识和数据可以被系统地利用、捕获，并主要集成在一起，共同训练视觉算法。然而，开发这样一个框架是具有挑战性的，因为领域知识通常以不同的形式存在，通常无法使用数据驱动的统计机器学习方法。为了克服这一挑战，研究团队系统地将领域知识转换为模型上的约束或伪数据，以便将其纳入统计学习方法。该项目包括系统地识别来自不同来源的知识，以及捕获知识的具体机制，并将其转换为易于自动机器学习方法访问的格式。该项目还包括证明所提出的框架对某些计算机视觉问题的有效性。该项目为研究生和本科生提供培训，并通过出版物和组织相关讲习班传播研究成果。