Becoming the expert - interactive multi-class machine teaching
Becoming the expert - interactive multi-class machine teaching
复制标题
DOI：
10.1109/cvpr.2015.7298877
复制
发表时间：
2015-04
期刊：
影响因子：
--
通讯作者：
Edward Johns;Oisin Mac Aodha;G. Brostow
中科院分区：
文献类型：
--
作者：
Edward Johns;Oisin Mac Aodha;G. Brostow
与机器相比，人类非常擅长将图像分类，特别是当他们拥有手头类别的先验知识时。如果没有这种先验信息，则需要以教学图像的形式进行监督。为了更快地学习类别，人们应该首先看到重要的和有代表性的图像，然后是不太重要的图像-或者根本不看。然而，图像的重要性是个人特定的，即一个教学图像是重要的学生，如果它改变了他们的整体能力，区分类。此外，学生不断学习，因此，虽然图像的重要性取决于他们目前的知识，它也随着时间的推移而变化。在这项工作中，我们提出了一个交互式的机器教学算法，使计算机教具有挑战性的视觉概念的人。我们的自适应算法选择，在线，标记图像从教学集应该显示给学生，因为他们学习。我们表明，概率模型的学生的能力和进步的教学策略，根据他们的正确和不正确的答案，产生更好的“专家”。我们使用真实的人类参与者在几个不同的和具有挑战性的现实世界的数据集。
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important and representative images first, followed by less important images later - or not at all. However, image-importance is individual-specific, i.e. a teaching image is important to a student if it changes their overall ability to discriminate between classes. Further, students keep learning, so while image-importance depends on their current knowledge, it also varies with time. In this work we propose an Interactive Machine Teaching algorithm that enables a computer to teach challenging visual concepts to a human. Our adaptive algorithm chooses, online, which labeled images from a teaching set should be shown to the student as they learn. We show that a teaching strategy that probabilistically models the student's ability and progress, based on their correct and incorrect answers, produces better `experts'. We present results using real human participants across several varied and challenging real-world datasets.