Perceptual Annotation: Measuring Human Vision to Improve Computer Vision
Perceptual Annotation: Measuring Human Vision to Improve Computer Vision
复制标题
感知注释：测量人类视觉以改善计算机视觉
DOI：
--
复制
发表时间：
2014
影响因子：
23.6
通讯作者：
David D. Cox
中科院分区：
文献类型：
--
作者：
W. Scheirer;Samuel E. Anthony;K. Nakayama;David D. Cox
对于计算机视觉中的许多问题，人类学习者比机器要好得多。人类拥有高度准确的内部识别和学习机制，但这些机制尚未被理解，并且通过一生对视觉世界的无偏见经验，他们经常可以获得更广泛的训练数据。我们建议使用视觉心理物理学来直接利用人类受试者的能力来构建更好的机器学习系统。首先，我们使用一个先进的在线心理测试平台，使新类型的注释数据可用于学习。其次，我们开发了一种技术，利用这些新的信息-“感知注释”-支持向量机。这种方法的一个关键直觉是，虽然大幅增加可用于训练给定系统的数据量和高质量标签可能仍然是不可行的，但测量逐个样本的难度和人类注释者的错误模式可以为正则化手头的系统解决方案提供重要信息。问题人脸检测的案例研究表明，这种方法在具有挑战性的FDDB数据集上产生了最先进的结果。
For many problems in computer vision, human learners are considerably better than machines. Humans possess highly accurate internal recognition and learning mechanisms that are not yet understood, and they frequently have access to more extensive training data through a lifetime of unbiased experience with the visual world. We propose to use visual psychophysics to directly leverage the abilities of human subjects to build better machine learning systems. First, we use an advanced online psychometric testing platform to make new kinds of annotation data available for learning. Second, we develop a technique for harnessing these new kinds of information-“perceptual annotations”-for support vector machines. A key intuition for this approach is that while it may remain infeasible to dramatically increase the amount of data and high-quality labels available for the training of a given system, measuring the exemplar-by-exemplar difficulty and pattern of errors of human annotators can provide important information for regularizing the solution of the system at hand. A case study for the problem face detection demonstrates that this approach yields state-of-the-art results on the challenging FDDB data set.