Visual Psychophysics for Making Face Recognition Algorithms More Explainable
Visual Psychophysics for Making Face Recognition Algorithms More Explainable
复制标题
DOI：
10.1007/978-3-030-01267-0_16
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Brandon RichardWebster;So Yon Kwon;Christopher Clarizio;Samuel E. Anthony;W. Scheirer
中科院分区：
文献类型：
--
作者：
Brandon RichardWebster;So Yon Kwon;Christopher Clarizio;Samuel E. Anthony;W. Scheirer
对面部感兴趣的科学领域已经开发了自己的一套概念和程序，用于理解目标模型系统（无论是人还是算法）在不同条件下如何感知面部。在计算机视觉中，这主要采取识别任务的数据集评估的形式，其中使用汇总统计来衡量进度。虽然总体性能不断提高，但理解失败的个别原因却很困难，因为并不总是清楚为什么特定的面孔无法被识别，或者为什么算法能够识别冒名顶替者。重要的是，研究视觉的其他领域已经通过使用视觉心理物理学解决了这个问题：对刺激的受控操纵以及对它们在模型系统中引起的反应的仔细研究。在本文中，我们建议视觉心理物理学是一种使人脸识别算法更易于解释的可行方法。开发了一套全面的程序来评估人脸识别算法的行为，然后将其部署在最先进的卷积神经网络和更基本但仍广泛使用的浅层和手工制作的基于特征的方法上。
Scientific fields that are interested in faces have developed their own sets of concepts and procedures for understanding how a target model system (be it a person or algorithm) perceives a face under varying conditions. In computer vision, this has largely been in the form of dataset evaluation for recognition tasks where summary statistics are used to measure progress. While aggregate performance has continued to improve, understanding individual causes of failure has been difficult, as it is not always clear why a particular face fails to be recognized, or why an impostor is recognized by an algorithm. Importantly, other fields studying vision have addressed this via the use of visual psychophysics: the controlled manipulation of stimuli and careful study of the responses they evoke in a model system. In this paper, we suggest that visual psychophysics is a viable methodology for making face recognition algorithms more explainable. A comprehensive set of procedures is developed for assessing face recognition algorithm behavior, which is then deployed over state-of-the-art convolutional neural networks and more basic, yet still widely used, shallow and handcrafted feature-based approaches.