RI: Small: Exploring Rationale behind Visual Understanding: Combining Attention and Reasoning

深度学习的最新进展导致模型在计算机视觉任务中表现出显着的性能提升。该项目旨在弥合当前智能系统性能的提高与复杂任务解决过程中缺乏理解之间的差距。以理解和建模这一过程为首要目标，本项目研究了两个相互交织的机制，即注意力和推理，并开发了一个健全的框架来整合这两个机制。这将是解开解决视觉任务过程和缓解机器学习中的黑箱问题的关键一步。这项研究将为机器建立注意力和推理能力，从而增强在广泛的人工智能任务中的应用，包括医疗诊断和治疗、机器人和教育。首席研究员将组织讲习班和研讨会，并公布项目结果。该项目还旨在通过K-12外展活动、学生指导和课程开发，将研究和教育结合起来，重点关注增加多样性。该项目侧重于数据集和模型的开发，以及为网络可视化、解释和诊断提供新的方法。更具体地说，该项目开发：(1)一个具有人眼运动和文本解释的新数据集，以了解影响任务性能的关键因素；(2)一个框架，其中在框架中设计的模型通过展示注意力和推理能力来演示任务解决过程的第一步；(3)一种考虑网络各层性能和可解释性的分层网络诊断方法。解决这些问题不仅可以提高模型的性能，而且可以打开视觉任务决策过程的黑箱以及深度神经网络的结构。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Recent progress in deep learning has resulted in models that show significant performance gains in computer vision tasks. This project aims to bridge the current gap between the increasing performance in intelligent systems and the lack of understanding in the complex task-solving process. With the overarching goal of understanding and modeling the process, this project studies two intertwined mechanisms heavily involved in task-solving -- attention and reasoning -- and develops a sound framework to integrate the two. It will serve as a critical step forward to untangling the process of solving a visual task and alleviating the black-box problem in machine learning. The research will build attention and reasoning capabilities into machines, thus empowering applications in a broad spectrum of artificial intelligence tasks including medical diagnosis and treatment, robotics, and education. The principal investigator will organize workshops and seminars, and make project results publicly available. The project also aims at integrated research and education with a focus on increased diversity, through K-12 outreach activities, student mentoring, and curriculum development.This project focuses on both dataset and model development, as well as enabling new methods for network visualization, interpretation, and diagnosis. More specifically, the project develops: (1) a new dataset with human eye movements and textual explanations, to understand critical factors that contribute to task performance; (2) a framework where models devised in the framework make a first step to demonstrate the process of task-solving by showing attention and reasoning capabilities; and (3) a novel layer-wise network diagnosis method considering both performance and interpretability of each network layer. Addressing these questions will not only boost model performance but open the black-box of the decision-making process of a visual task as well as the structure of the deep neural networks.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.