Song Yiying, Qu Yukun, Xu Shan, Liu Jia
Beijing Key Laboratory of Applied Experimental Psychology, Faculty of Psychology, Beijing Normal University, Beijing, China.
State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China.
Front Comput Neurosci. 2021 Jan 26;14:601314. doi: 10.3389/fncom.2020.601314. eCollection 2020.
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.
如今，深度卷积神经网络（DCNN）在具有挑战性的复杂任务中能够达到人类的表现水平，但DCNN是否通过类似人类的过程实现类似人类的表现仍不明确。在此，我们应用了一种反向相关方法，以便在进行面部性别分类时，明确DCNN和人类的表征。我们发现，人类和典型的DCNN（VGG-Face）在执行此任务时使用了类似的关键信息，这些信息主要位于低空间频率处。重要的是，VGG-Face像人类一样在从属级别（即识别）对处理面部进行了预训练，这种先前的任务经验对于这种表征相似性似乎是必要的，因为AlexNet是一个在基本级别（即分类）对处理物体进行预训练的DCNN，它成功地进行了性别分类，但依赖的是完全不同的表征。总之，虽然DCNN和人类依靠不同的硬件集来处理面部，但它们可以使用类似且与实现无关的表征来实现相同的计算目标。
