The state of modelling face processing in humans with deep learning
Bibliographic Data
| ID | 9620131 |
|---|---|
| Authors | P Jonathon Phillips (0000-0001-6284-5197, National Institute of Standards and Technology Gaithersburg Maryland USA), David White (0000-0002-6366-2699, School of Psychology UNSW Sydney Sydney New South Wales Australia, corresponding author) |
| Year | 2025 |
| Volume | 117 |
| Issue | 2 |
| Pages | 656-676 |
| Publication date | 2025-05-14 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | British Journal of Psychology (JOURNAL) |
| Journal identifiers | ISSN: 0007-1269 • E-ISSN: 2044-8295 |
| Publisher | Wiley (PUBLISHER • GB) |
| DOI | 10.1111/bjop.12794 |
| PMID | 40364689 |
| OpenAlex | W4410377490 |
| Language | EN |
| Citations received | 3 |
| References cited | 117 |
Deep learning models trained for facial recognition now surpass the highest performing human participants. Recent evidence suggests that they also model some qualitative aspects of face processing in humans. This review compares the current understanding of deep learning models with psychological models of the face processing system. Psychological models consist of two components that operate on the information encoded when people perceive a face, which we refer to here as ‘face codes’. The first component, the core system, extracts face codes from retinal input that encode invariant and changeable properties. The second component, the extended system, links face codes to personal information about a person and their social context. Studies of face codes in existing deep learning models reveal some surprising results. For example, face codes in networks designed for identity recognition also encode expression information, which contrasts with psychological models that separate invariant and changeable properties. Deep learning can also be used to implement candidate models of the face processing system, for example to compare alternative cognitive architectures and codes that might support interchange between core and extended face processing systems. We conclude by summarizing seven key lessons from this research and outlining three open questions for future study
Cognition · Cognitive psychology · Cognitive science · Component (thermodynamics) · Context (archaeology) · Deep learning · ENCODE · Facial recognition system · Information processing · Machine learning · Pattern recognition (psychology) · Artificial Intelligence · Computer Science · Face recognition and analysis · Face Recognition and Perception · Neuroscience · Psychology · Visual Attention and Saliency Detection
Variability in photos of the same face
Visual objects in context
A Unified Account of the Effects of Distinctiveness, Inversion, and Race in Face Recognition
The distributed human neural system for face perception
Deep learning
Computational insights into human perceptual expertise for familiar and unfamiliar face recognition
Seeing through disguise
The neural processing of familiar and unfamiliar faces
Understanding face recognition
Understanding face recognition with an interactive activation model
Understanding person perception
The faces that launched a thousand slips
Using deep neural networks to disentangle visual and semantic information in human perception and memory
The Role of Gestures and Facial Cues in Second Language Listening Comprehension
| Unique citing works | 3 |
|---|---|
| Citations per year | 3 |
| Citation span | 2026 - 2026 (1) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 3 |