CAREER: Vision Systems for an Evolving World

职业：面向不断发展的世界的视觉系统

• 批准号: 2144194
• 负责人: Judy Hoffman
• 金额: $ 58.99万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2027-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2144194&HistoricalAwards=false
• 关键词: CAREER; Vision; Systems; Evolving; World

When transitioning into a dark room most people initially struggle to see, but are quickly able to adjust and see in the new setting. In fact, people continue to see and understand the world around them even as the appearance of the world changes in many different ways. In contrast, our computer vision systems have limited ability to understand the world if it changes. Imagine if the first time one drove at twilight or in the snow one could no longer recognize the road. No doubt, driver’s training would require many hours of sitting in the passenger seat at all times of day, within different weather conditions, across different cities, and so on before allowing a new driver behind the wheel. This project aims to study and build new models, algorithms, and measures of success enabling the next generation of visual recognition systems to be resilient to an evolving visual world. The project will integrate research with education and outreach to K-12 students.This project advocates for resilient vision systems through a new integrated approach which iterates between generalizing across available visual domains and rapidly adapting given new domain data. Prior approaches optimize for independent criteria, either generalization across multiple domains, or adaptation to a new target domain, which limits advancement towards the larger goal of creating vision systems that can operate in more domains over time. Further, existing solutions are slow to adapt, relying on substantial new observations before updates can be made. The project will work on: 1) Model design and learning approaches for multi-domain generalization that facilitates future adaptation. 2) Transformative visual domain adaptation algorithms that are capable of rapidly adapting to a target domain using limited target observations and without accessing a large auxiliary source of data, reducing compute demands. 3) Algorithms that enable vision systems to expand the set of domains they can successfully operate in over time. Finally, this project will introduce a benchmark and new evaluation protocols to measure the resilience of visual recognition models to changing domains.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.

当进入一个黑暗的房间时，大多数人最初都很难看清，但很快就能调整并在新的环境中看到。事实上，人们继续看到和理解他们周围的世界，即使世界的外观以许多不同的方式发生变化。相比之下，我们的计算机视觉系统在世界发生变化时理解世界的能力有限。想象一下，如果一个人第一次在黄昏或雪地里开车，他再也认不出路了。毫无疑问，驾驶员的培训需要在一天中的任何时候，在不同的天气条件下，在不同的城市，等等，在允许一个新的司机开车之前，都要坐在乘客座位上好几个小时。该项目旨在研究和构建新的模型，算法和成功措施，使下一代视觉识别系统能够适应不断变化的视觉世界。该项目将把研究与教育结合起来，并推广到K-12学生。该项目通过一种新的综合方法倡导弹性视觉系统，该方法在现有视觉领域的概括和快速适应给定的新领域数据之间进行迭代。先前的方法针对独立的标准进行了优化，无论是跨多个域的泛化，还是适应新的目标域，这都限制了朝着创建可以随着时间的推移在更多域中操作的视觉系统的更大目标的前进。此外，现有的解决方案适应缓慢，在进行更新之前依赖于大量的新观察。该项目将致力于：1）多领域泛化的模型设计和学习方法，以促进未来的适应。2)变换视觉域自适应算法，其能够使用有限的目标观测快速适应目标域，而无需访问大量辅助数据源，从而减少计算需求。3)算法使视觉系统能够扩展它们可以随着时间的推移成功操作的域集合。最后，该项目将引入一个基准和新的评估协议，以衡量视觉识别模型对不断变化的领域的适应能力。该奖项反映了NSF的法定使命，并被认为值得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来支持。