Social Trait Information in Deep Convolutional Neural Networks Trained for Face Identification.
Social Trait Information in Deep Convolutional Neural Networks Trained for Face Identification.
复制标题
深度卷积神经网络中的社会特质信息接受了面部识别的培训。
DOI：
10.1111/cogs.12729
复制
发表时间：
2019-06
影响因子：
2.5
通讯作者：
O'Toole AJ
中科院分区：
文献类型：
--
作者：
Parde CJ;Hu Y;Castillo C;Sankaranarayanan S;O'Toole AJ
面孔提供了关于一个人的身份以及他们的性别、年龄和种族的信息。人们还可以从对面孔的判断中推断出社会和个性特征，这可能会对社会和个人产生重要的影响。近年来，深度卷积神经网络(DCNN)已经被证明擅长从视点、光照、表情和外观变化很大的图像中表示人脸的身份。这些算法是在灵长类视觉皮质上模拟的，由多个模拟神经元的处理层组成。在这里，我们检查了接受过人脸识别训练的DCNN是否也保留了支持社会特质推断的面部信息的表征。参与者根据18种不同的个性特征对男性和女性的面孔进行了评分。线性分类器通过交叉验证进行训练，以根据在用于人脸识别的DCNN顶层出现的512维人脸表示来预测人类分配的特征评级。该网络用10575个身份的494,414张图像进行了训练，由7层和1980万个参数组成。该电视网制作的顶级DCNN专题节目对人类分配的社会特征档案的预测准确率很高。人类对个体特征的评分也得到了准确的预测。我们的结论是，从DCNN中出现的面部表示保留了超出其训练严格限制的面部信息。
Faces provide information about a person’s identity, as well as their sex, age, and ethnicity. People also infer social and personality traits from the face — judgments that can have important societal and personal consequences. In recent years, deep convolutional neural networks (DCNNs) have proven adept at representing the identity of a face from images that vary widely in viewpoint, illumination, expression, and appearance. These algorithms are modeled on the primate visual cortex and consist of multiple processing layers of simulated neurons. Here, we examined whether a DCNN trained for face identification also retains a representation of the information in faces that supports social-trait inferences. Participants rated male and female faces on a diverse set of 18 personality traits. Linear classifiers were trained with cross validation to predict human-assigned trait ratings from the 512 dimensional representations of faces that emerged at the top-layer of a DCNN trained for face identification. The network was trained with 494,414 images of 10,575 identities and consisted of seven layers and 19.8 million parameters. The top-level DCNN features produced by the network predicted the human-assigned social trait profiles with good accuracy. Human-assigned ratings for the individual traits were also predicted accurately. We conclude that the face representations that emerge from DCNNs retain facial information that goes beyond the strict limits of their training.
登录
查看更多内容
DOI：
10.1109/tpami.2005.90
发表时间：
2005-05-01
影响因子：
23.6
作者：
O'Toole, AJ;Harms, J;Abdi, H
通讯作者：
Abdi, H
影响因子：
7.6
作者：
Cloutier, J;Mason, MF;Macrae, CN
通讯作者：
Macrae, CN
影响因子：
2.1
作者：
Montepare, JM;Dobish, H
通讯作者：
Dobish, H
影响因子：
2.6
作者：
Gobbini, M. Ida;Haxby, James V.
通讯作者：
Haxby, James V.
影响因子：
4
作者：
BRUCE, V;YOUNG, A
通讯作者：
YOUNG, A