敏捷建模：从概念到分类器只需几分钟
Agile Modeling: From Concept to Classifier in Minutes
AI总结：
本文提出敏捷建模方法，通过实时用户交互使非专家在30分钟内为任意主观视觉概念创建图像分类器，实验证明其优于传统众包方式。
摘要：
计算机视觉在细微主观用例中的应用正在增长。虽然众包在大多数客观任务（如标记“斑马”）中为视觉社区服务良好，但在概念存在大量主观性的任务（如识别“美食金枪鱼”）上，它现在表现不佳。然而，让任何用户为其概念开发分类器在技术上是困难的：用户既不是机器学习专家，也没有耐心标记数千个示例。为此，我们引入了敏捷建模问题：通过实时用户参与循环交互，将任何主观视觉概念转化为计算机视觉模型的过程。我们实例化了一个用于图像分类的敏捷建模原型，并通过用户研究（N=14）表明，用户可以在30分钟内以最小努力创建分类器。我们将这种用户驱动过程与传统众包范式进行比较，发现众包的概念往往与用户的不同，尤其是当概念变得更加主观时。最后，我们通过模拟用户为ImageNet21k类别训练分类器来扩展实验，进一步证明其有效性。
英文摘要：
The application of computer vision to nuanced subjective use cases is growing. While crowdsourcing has served the vision community well for most objective tasks (such as labeling a "zebra"), it now falters on tasks where there is substantial subjectivity in the concept (such as identifying "gourmet tuna"). However, empowering any user to develop a classifier for their concept is technically difficult: users are neither machine learning experts, nor have the patience to label thousands of examples. In reaction, we introduce the problem of Agile Modeling: the process of turning any subjective visual concept into a computer vision model through a real-time user-in-the-loop interactions. We instantiate an Agile Modeling prototype for image classification and show through a user study (N=14) that users can create classifiers with minimal effort under 30 minutes. We compare this user driven process with the traditional crowdsourcing paradigm and find that the crowd's notion often differs from that of the user's, especially as the concepts become more subjective. Finally, we scale our experiments with simulations of users training classifiers for ImageNet21k categories to further demonstrate the efficacy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
