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.

中文翻译：

---

深度卷积神经网络和人脸处理中与实现无关的表示

如今，深度卷积神经网络 (DCNN) 可以在具有挑战性的复杂任务中匹配人类的表现，但 DCNN 是否通过类人的过程实现类人的表现仍然未知。在这里，我们在执行面部性别分类时应用了一种反相关方法来明确表示 DCNN 和人类。我们发现人类和典型的 DCNN VGG-Face 使用类似的关键信息来完成这项任务，这些信息主要位于低空间频率。重要的是，VGG-Face 被预先训练以像人类一样在从属级别（即识别）处理人脸的先前任务经验似乎对于这种表示相似性是必要的，因为 AlexNet，一个经过预训练以处理对象的 DCNN在基本层面（即分类），在性别分类方面取得了成功，但依赖于完全不同的表现形式。总而言之，尽管 DCNN 和人类依赖不同的硬件来处理人脸，但它们可以使用类似且与实现无关的表示来实现相同的计算目标。