EAGER: Leveraging Synthetic Data for Visual Reasoning and Representation Learning with Minimal Human Supervision

该项目研究如何使用计算机图形创建的合成数据用于开发能够理解视觉数据的算法。合成数据提供了现实世界图像难以获得的灵活性，并使人们有机会探索仅靠现实世界图像难以解决的问题。该项目开发了关于对象遮挡的推理和自监督表示学习的新算法，其中有用的图像特征是在不借助人类标注的语义标签的情况下开发的。该项目提供了新的算法，有可能使自主系统和安全方面的应用受益。除了科学影响，该项目还开展了补充的教育和推广活动，让学生参与研究和STEM。这项研究探索了从合成数据中学习视觉推理和表征学习的新算法。虽然合成数据的使用在计算机视觉中有很长的历史，但它主要用于补充自然图像数据，以解决标准任务。相比之下，这个项目使用合成数据在相对未被探索的问题上取得进展，在这些问题中，地面真相很难获得给定的真实世界图像。该项目包括三个主要推力，每个推力都利用了这样一个事实，即用户可以完全控制合成数据集中发生的一切。在推力I中，它研究了一种使用合成数据进行表征学习的新方法，在推力II中，它扩展了算法以分离任务特定和通用的特征。最后，在推力III中，它探索了一种关于物体遮挡的新的推理方法。

This project investigates how synthetic data created using computer graphics can be used for developing algorithms that understand visual data. Synthetic data provides flexibility that is difficult to obtain with real-world imagery, and enables opportunities to explore problems that would be difficult to solve with real-world imagery alone. This project develops new algorithms for reasoning about object occlusions, and for self-supervised representation learning, in which useful image features are developed without the aid of human-annotated semantic labels. The project provides new algorithms that have the potential to benefit applications in autonomous systems and security. In addition to scientific impact, the project performs complementary educational and outreach activities that engage students in research and STEM.This research explores novel algorithms that learn from synthetic data for visual reasoning and representation learning. While the use of synthetic data has a long history in computer vision, it has mainly been used to complement natural image data to solve standard tasks. In contrast, this project uses synthetic data to make advances in relatively unexplored problems, in which ground-truth is difficult to obtain given real-world imagery. The project consists of three major thrusts, each of which exploits the fact that a user has full control of everything that happens in a synthetic dataset. In Thrust I, it investigates a novel approach to representation learning using synthetic data, and in Thrust II, it extends the algorithm to disentangle task-specific and general-purpose features. Finally, in Thrust III, it explores a novel approach for reasoning about object occlusions.