AUTHOR=Song Yiying , Qu Yukun , Xu Shan , Liu Jia TITLE=Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces JOURNAL=Frontiers in Computational Neuroscience VOLUME=14 YEAR=2021 URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2020.601314 DOI=10.3389/fncom.2020.601314 ISSN=1662-5188 ABSTRACT=

Deep convolutional neural networks (DCNN) nowadays can match human performance in challenging complex tasks, but it remains unknown whether DCNNs achieve human-like performance through human-like processes. Here we applied a reverse-correlation method to make explicit representations of DCNNs and humans when performing face gender classification. We found that humans and a typical DCNN, VGG-Face, used similar critical information for this task, which mainly resided at low spatial frequencies. Importantly, the prior task experience, which the VGG-Face was pre-trained to process faces at the subordinate level (i.e., identification) as humans do, seemed necessary for such representational similarity, because AlexNet, a DCNN pre-trained to process objects at the basic level (i.e., categorization), succeeded in gender classification but relied on a completely different representation. In sum, although DCNNs and humans rely on different sets of hardware to process faces, they can use a similar and implementation-independent representation to achieve the same computation goal.