The Face Inversion Effect in Deep Convolutional Neural Networks

Published on May 9, 2022

Imagine a world where faces can turn into objects… well, in the realm of artificial neural networks, it’s not so far-fetched! Scientists have investigated the phenomenon known as the face inversion effect (FIE) in a deep convolutional neural network called VGG-Face. Just like humans, this network specializes in recognizing faces. It turns out that when faces are inverted, VGG-Face struggles more compared to its counterpart network designed for processing objects. This fascinating discovery suggests that inverted faces are processed as objects in this artificial face system. By analyzing the network’s classification errors and internal representations, researchers observed that VGG-Face miscategorized inverted faces as objects and represented them similarly to actual objects. These findings provide further support for the idea that inverted faces activate face-specific mechanisms differently from upright faces. To dive deeper into this captivating research and explore the intricate world of artificial face recognition systems, check out the full article!

The face inversion effect (FIE) is a behavioral marker of face-specific processing that the recognition of inverted faces is disproportionately disrupted than that of inverted non-face objects. One hypothesis is that while upright faces are represented by face-specific mechanism, inverted faces are processed as objects. However, evidence from neuroimaging studies is inconclusive, possibly because the face system, such as the fusiform face area, is interacted with the object system, and therefore the observation from the face system may indirectly reflect influences from the object system. Here we examined the FIE in an artificial face system, visual geometry group network-face (VGG-Face), a deep convolutional neural network (DCNN) specialized for identifying faces. In line with neuroimaging studies on humans, a stronger FIE was found in VGG-Face than that in DCNN pretrained for processing objects. Critically, further classification error analysis revealed that in VGG-Face, inverted faces were miscategorized as objects behaviorally, and the analysis on internal representations revealed that VGG-Face represented inverted faces in a similar fashion as objects. In short, our study supported the hypothesis that inverted faces are represented as objects in a pure face system.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>