RI: Small: Debugging Machine Visual Recognition via Humans in the Loop

RI：小型：通过人在循环中调试机器视觉识别

• 批准号: 1115719
• 负责人: Devi Parikh
• 金额: $ 15万
• 依托单位: Toyota Technological Institute at Chicago
• 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: 2011-09-01 至 2013-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1115719&HistoricalAwards=false
• 关键词: RI; Small; Debugging; Machine; Visual

The problem of visual recognition is fundamental towards the goal of automatic image understanding. While a large number of efforts have been made in the computer vision community, machine performance at these tasks remains significantly inferior to human ability. The overarching goal of this project is to leverage the best known visual recognition system - the human visual recognition system. This project employs a "Human Debugging" paradigm to replace various components of a machine vision pipeline with human subjects, and examines the resultant effect on recognition performance. Meaningful comparisons provide valuable insights and pinpoint aspects of the machine vision pipeline that are performance bottlenecks and require future research efforts. Specifically, the project considers the problems of image classification and object detection, and explores the roles of local and global information, as well part-detection, spatial modeling and contextual reasoning (including non-maximal suppression) for these problems respectively. This project touches on a wide range of problems in visual recognition including object recognition, scene recognition and object detection. This novel paradigm of identifying weak links in computational models via humans in the loop is also applicable to other vision problems, as well as other sub-fields in AI. By sharing all collected data and results, and through organized conferences and workshops, this project will initiate and fuel a dialogue with the research community about leveraging humans to advance computer vision. More broadly, this work encourages the involvement of young women and undergraduate students in computer science research.

视觉识别问题是实现自动图像理解的基础。虽然计算机视觉领域已经做出了大量的努力，但机器在这些任务中的性能仍然明显低于人类的能力。该项目的总体目标是利用最著名的视觉识别系统--人类视觉识别系统。该项目采用“人类调试”范例，用人类受试者取代机器视觉流水线的各种组件，并检查由此产生的对识别性能的影响。有意义的比较提供了有价值的见解和准确的机器视觉管道的方面，这些方面是性能瓶颈，需要未来的研究努力。具体地说，该项目考虑了图像分类和目标检测问题，并分别探讨了局部信息和全局信息的作用，以及针对这些问题的局部检测、空间建模和上下文推理(包括非最大抑制)。该项目涉及视觉识别中的一系列问题，包括对象识别、场景识别和对象检测。这种通过循环中的人来识别计算模型中的薄弱环节的新范式也适用于其他视觉问题，以及人工智能中的其他子领域。通过分享所有收集到的数据和结果，并通过有组织的会议和研讨会，该项目将启动并推动与研究界关于利用人类推进计算机视觉的对话。更广泛地说，这项工作鼓励年轻女性和本科生参与计算机科学研究。