Seeing through disguise: Getting to know you with a deep convolutional neural network.
Seeing through disguise: Getting to know you with a deep convolutional neural network.
复制标题
看穿伪装：用深度卷积神经网络了解你。
DOI：
10.1016/j.cognition.2021.104611
复制
发表时间：
2021-06
期刊：
影响因子：
3.4
通讯作者：
O'Toole AJ
中科院分区：
文献类型：
--
作者：
Noyes E;Parde CJ;Colón YI;Hill MQ;Castillo CD;Jenkins R;O'Toole AJ
人们使用伪装看起来不像自己（逃避）或看起来像别人（模仿）。逃避伪装挑战人类在不同图像中识别身份的能力;模仿挑战人类区分人的能力。个人对个人面孔的熟悉有助于人类识破伪装。在这里，我们提出了一个基于高级视觉学习机制的熟悉度模型，我们使用深度卷积神经网络（DCNN）进行了人脸识别训练。DCNN生成了一个人脸空间，其中身份和图像共存于一个统一的计算框架中，该框架是围绕身份而不是视网膜病变进行分类结构化的。这允许同时操纵对比身份和集群图像的机制。在实验1中，我们测量了DCNN在没有伪装和伪装条件下识别人脸的基线准确度（不熟悉条件）。伪装影响DCNN的表现，就像它影响人类对伪装的陌生面孔的表现一样（参见）。在实验2中，我们通过对每个身份的多个图像的DCNN生成的表示进行平均来模拟个人身份的熟悉度。平均化改进了DCNN对逃避伪装中的面部的识别，但降低了DCNN区分相似外观的身份的能力。在实验3中，我们实施了对比学习技术，以同时教授不同个体之间的DCNN外观变化和身份对比。这有利于识别与逃避和冒充伪装。熟悉的人脸识别需要将相同身份的图像分组在一起并分离不同身份的能力。深度网络为人脸识别提供了一种高级视觉表示，同时支持这两种人脸学习机制。
People use disguise to look unlike themselves (evasion) or to look like someone else (impersonation). Evasion disguise challenges human ability to see an identity across variable images; Impersonation challenges human ability to tell people apart. Personal familiarity with an individual face helps humans to see through disguise. Here we propose a model of familiarity based on high-level visual learning mechanisms that we tested using a deep convolutional neural network (DCNN) trained for face identification. DCNNs generate a face space in which identities and images co-exist in a unified computational framework, that is categorically structured around identity, rather than retinotopy. This allows for simultaneous manipulation of mechanisms that contrast identities and cluster images. In Experiment 1, we measured the DCNN’s baseline accuracy (unfamiliar condition) for identification of faces in no disguise and disguise conditions. Disguise affected DCNN performance in much the same way it affects human performance for unfamiliar faces in disguise (cf.). In Experiment 2, we simulated familiarity for individual identities by averaging the DCNN-generated representations from multiple images of each identity. Averaging improved DCNN recognition of faces in evasion disguise, but reduced the ability of the DCNN to differentiate identities of similar appearance. In Experiment 3, we implemented a contrast learning technique to simultaneously teach the DCNN appearance variation and identity contrasts between different individuals. This facilitated identification with both evasion and impersonation disguise. Familiar face recognition requires an ability to group images of the same identity together and separate different identities. The deep network provides a high-level visual representation for face recognition that supports both of these mechanisms of face learning simultaneously.
登录
查看更多内容
影响因子：
5.4
作者：
Kramer, Robin S. S.;Young, Andrew W.;Burton, A. Mike
通讯作者：
Burton, A. Mike
影响因子：
4.1
作者：
DIAMOND, R;CAREY, S
通讯作者：
CAREY, S
DOI：
10.1080/14640749408401141
发表时间：
1994-02-01
期刊：
QUARTERLY JOURNAL OF EXPERIMENTAL PSYCHOLOGY SECTION A-HUMAN EXPERIMENTAL PSYCHOLOGY
影响因子：
--
作者：
BRUCE, V
通讯作者：
BRUCE, V
影响因子：
2.6
作者：
Burton, AM;Jenkins, R;White, D
通讯作者：
White, D
影响因子：
1.7
作者：
Clutterbuck, R;Johnston, RA
通讯作者：
Johnston, RA