Face Recognition Depends on Specialized Mechanisms Tuned to View-Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition

Naphtali Abudarham, Idan Grosbard, Galit Yovel*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Face recognition is a computationally challenging classification task. Deep convolutional neural networks (DCNNs) are brain-inspired algorithms that have recently reached human-level performance in face and object recognition. However, it is not clear to what extent DCNNs generate a human-like representation of face identity. We have recently revealed a subset of facial features that are used by humans for face recognition. This enables us now to ask whether DCNNs rely on the same facial information and whether this human-like representation depends on a system that is optimized for face identification. In the current study, we examined the representation of DCNNs of faces that differ in features that are critical or non-critical for human face recognition. Our findings show that DCNNs optimized for face identification are tuned to the same facial features used by humans for face recognition. Sensitivity to these features was highly correlated with performance of the DCNN on a benchmark face recognition task. Moreover, sensitivity to these features and a view-invariant face representation emerged at higher layers of a DCNN optimized for face recognition but not for object recognition. This finding parallels the division to a face and an object system in high-level visual cortex. Taken together, these findings validate human perceptual models of face recognition, enable us to use DCNNs to test predictions about human face and object recognition as well as contribute to the interpretability of DCNNs.

Original languageEnglish
Article numbere13031
JournalCognitive Science
Volume45
Issue number9
DOIs
StatePublished - Sep 2021

Funding

FundersFunder number
Joint China-Israel
NSFC-ISF
NSFC‐ISF2383/18

    Keywords

    • Artificial intelligence
    • Deep convolutional neural networks
    • Explainability
    • Face recognition
    • Face space
    • High-level visual system

    Fingerprint

    Dive into the research topics of 'Face Recognition Depends on Specialized Mechanisms Tuned to View-Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition'. Together they form a unique fingerprint.

    Cite this