EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human-like face pareidolia emerges in deep neural networks optimized for face and object recognition

Pranjul Gupta iD, Katharina Dobs iD

PLOS Computational Biology · 27.01.2025 · 21 (1) · e1012751

DOI: 10.1371/journal.pcbi.1012751 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 27.01.2025. Verfasst von Pranjul Gupta und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Experimental Psychology, Justus Liebig University Giessen, Giessen, Germany. Hauptthemen laut MEDLINE: Neural Networks, Computer, Facial Recognition, Pattern Recognition, Visual, Face. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), Excellence Program of the Hessian Ministry of Higher Education, Science, Research and the Arts, Hessisches Ministerium für Wissenschaft und Forschung, Kunst und Kultur.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The human visual system possesses a remarkable ability to detect and process faces across diverse contexts, including the phenomenon of face pareidolia—–seeing faces in inanimate objects. Despite extensive research, it remains unclear why the visual system employs such broadly tuned face detection capabilities. We hypothesized that face pareidolia results from the visual system’s optimization for recognizing both faces and objects. To test this hypothesis, we used task-optimized deep convolutional neural networks (CNNs) and evaluated their alignment with human behavioral signatures and neural responses, measured via magnetoencephalography (MEG), related to pareidolia processing. Specifically, we trained CNNs on tasks involving combinations of face identification, face detection, object categorization, and object detection. Using representational similarity analysis, we found that CNNs that included object categorization in their training tasks represented pareidolia faces, real faces, and matched objects more similarly to neural responses than those that did not. Although these CNNs showed similar overall alignment with neural data, a closer examination of their internal representations revealed that specific training tasks had distinct effects on how pareidolia faces were represented across layers. Finally, interpretability methods revealed that only a CNN trained for both face identification and object categorization relied on face-like features—such as ‘eyes’—to classify pareidolia stimuli as faces, mirroring findings in human perception. Our results suggest that human-like face pareidolia may emerge from the visual system’s optimization for face identification within the context of generalized object categorization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerFacial RecognitionPattern Recognition, VisualFaceHumansMaleFemaleMagnetoencephalographyAdultYoung AdultComputational Biology

Autor:innen und Institutionen

  • Department of Experimental Psychology, Justus Liebig University Giessen, Giessen, Germany.
  • Center for Mind, Brain, and Behavior, Universities of Marburg, Giessen and Darmstadt, Marburg, Germany.

ORCID-Profile: Pranjul Gupta, Katharina Dobs

Förderung

  • Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)
  • Excellence Program of the Hessian Ministry of Higher Education, Science, Research and the Arts
  • Hessisches Ministerium für Wissenschaft und Forschung, Kunst und Kultur

Zitieren

APA

Gupta, P., & Dobs, K. (2025). Human-like face pareidolia emerges in deep neural networks optimized for face and object recognition. PLOS Computational Biology, 21(1), e1012751. https://doi.org/10.1371/journal.pcbi.1012751

Vancouver

Gupta P, Dobs K. Human-like face pareidolia emerges in deep neural networks optimized for face and object recognition. PLOS Computational Biology. 2025;21(1):e1012751. doi:10.1371/journal.pcbi.1012751

BibTeX
@article{Gupta2025,
  author = {Gupta, Pranjul and Dobs, Katharina},
  title = {Human-like face pareidolia emerges in deep neural networks optimized for face and object recognition},
  journal = {PLOS Computational Biology},
  year = {2025},
  volume = {21},
  number = {1},
  pages = {e1012751},
  doi = {10.1371/journal.pcbi.1012751}
}
Kostenlos starten →