Face Recognition by Humans and Machines: Three Fundamental Advances from Deep Learning.
Face Recognition by Humans and Machines: Three Fundamental Advances from Deep Learning.
复制标题
人类和机器的人脸识别：深度学习的三个基本进步
DOI：
10.1146/annurev-vision-093019-111701
复制
发表时间：
2021-09-15
影响因子：
6
通讯作者：
Castillo CD
中科院分区：
文献类型：
--
作者：
O'Toole AJ;Castillo CD
深度学习模型目前在现实世界的人脸识别任务中达到了人类的水平。我们回顾了使用基于深度学习的计算方法来理解人脸处理的科学进展。本综述围绕三个基本进展展开。首先，训练用于人脸识别的深度网络生成一种表示，该表示保留有关人脸的结构化信息（例如，身份、人口统计、外观、社会特征、表情）和输入图像（例如，视点、照明）。这迫使我们重新思考视觉中逆光学问题的可能解决方案。其次，深度学习模型表明，人脸的高级视觉表征不能用可解释的特征来理解。这对理解高级视觉皮层中的神经调节和种群编码具有启示意义。第三，深度网络中的学习是一个多步骤的过程，它迫使理论考虑不同类别的学习，这些学习可以重叠，随着时间的推移积累和相互作用。不同的学习类型需要模拟人脸处理技能、跨种族效应和对个体面孔的熟悉程度的发展。
Deep learning models currently achieve human levels of performance on real-world face recognition tasks. We review scientific progress in understanding human face processing using computational approaches based on deep learning. This review is organized around three fundamental advances. First, deep networks trained for face identification generate a representation that retains structured information about the face (e.g., identity, demographics, appearance, social traits, expression) and the input image (e.g., viewpoint, illumination). This forces us to rethink the universe of possible solutions to the problem of inverse optics in vision. Second, deep learning models indicate that high-level visual representations of faces cannot be understood in terms of interpretable features. This has implications for understanding neural tuning and population coding in the high-level visual cortex. Third, learning in deep networks is a multistep process that forces theoretical consideration of diverse categories of learning that can overlap, accumulate over time, and interact. Diverse learning types are needed to model the development of human face processing skills, cross-race effects, and familiarity with individual faces.
登录
查看更多内容
影响因子：
2.5
作者：
Azevedo, Frederico A. C.;Carvalho, Ludmila R. B.;Herculano-Houzel, Suzana
通讯作者：
Herculano-Houzel, Suzana
影响因子：
1.7
作者：
Barlow, H B
通讯作者：
Barlow, H B
影响因子：
56.9
作者：
Bashivan, Pouya;Kar, Kohitij;DiCarlo, James J.
通讯作者：
DiCarlo, James J.
影响因子：
4.7
作者：
Crosswhite, Nate;Byrne, Jeffrey;Zisserman, Andrew
通讯作者：
Zisserman, Andrew
影响因子：
4
作者：
BRUCE, V;YOUNG, A
通讯作者：
YOUNG, A