EAGER: Quantifying and Reducing Data Bias in Object Detection Using Physics-based Image Synthesis

EAGER：使用基于物理的图像合成来量化和减少物体检测中的数据偏差

• 批准号: 1738063
• 负责人: Kate Saenko
• 金额: $ 5.51万
• 依托单位: Trustees of Boston University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-09-01 至 2018-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1738063&HistoricalAwards=false
• 关键词: EAGER; Quantifying; Reducing; Data; Bias

This project develops improved computer vision methods for automatic recognition of arbitrary objects in images from realistic environments. Object recognition is typically performed by fitting a function that maps an image to likely object locations and labels. Such a function is fitted (trained) on a database of example images along with their human-assigned object locations and labels. This research can result in more accurate visual perception for socially relevant applications, such as robots performing household tasks, assisting the elderly, responding to disasters and quickly learning new manufacturing and service skills. It can also provide a common codebase for the wider community, new dataset challenges for domain adaptation problems, the dissemination of scientific and technical results and associated courseware, and specific outreach to ensure broad participation of underrepresented groups.The specific research agenda is structured around two aims. The first aim is to establish bounds on the coverage of latent physical factors in datasets needed for human-level performance on arbitrary domains. The study involves both existing datasets and new datasets generated using graphics rendering techniques at various degrees of photorealism. The goal is to develop a theory of the physical complexity of a given dataset and how it affects generalization to real world object recognition tasks, with respect to a given image representation and learning framework. Physical parameters include but are not limited to: 3D shape, surface color, texture, background/scene, camera viewpoint, sensor noise, lighting, specularities and cast shadows. The second research aim is to learn image representations invariant to some of the physical causes of data bias. The goal is to develop model and representation learning methods that are able to learn from a combination of real and non-photorealistic synthetic data, and are resistant to common sources of data bias. The representations include simple edge-based descriptors, and more generally hierarchical representations based on layers of convolution and pooling operations.

该项目开发了改进的计算机视觉方法，用于自动识别现实环境中图像中的任意对象。对象识别通常通过拟合将图像映射到可能的对象位置和标签的函数来执行。这样的函数被安装（训练）在示例图像及其人工指定的对象位置和标签的数据库上。这项研究可以为社会相关应用带来更准确的视觉感知，例如机器人执行家务、帮助老年人、应对灾难以及快速学习新的制造和服务技能。它还可以为更广泛的社区提供通用代码库、领域适应问题的新数据集挑战、科学和技术成果及相关课件的传播以及确保代表性不足群体的广泛参与的具体外展活动。具体的研究议程围绕两个目标构建目标。第一个目标是对任意领域的人类水平表现所需的数据集中潜在物理因素的覆盖范围建立界限。该研究涉及现有数据集和使用不同真实感程度的图形渲染技术生成的新数据集。目标是针对给定的图像表示和学习框架，开发给定数据集的物理复杂性及其如何影响现实世界对象识别任务的泛化的理论。物理参数包括但不限于：3D 形状、表面颜色、纹理、背景/场景、相机视点、传感器噪声、照明、镜面反射和投射阴影。第二个研究目标是学习对数据偏差的某些物理原因不变的图像表示。目标是开发模型和表示学习方法，能够从真实和非真实合成数据的组合中学习，并且能够抵抗常见的数据偏差来源。这些表示包括简单的基于边缘的描述符，以及更一般的基于卷积和池化操作层的分层表示。