EUVIMEDEUVIMED entdecken
Crossref

Humans and convolutional neural networks prioritize similar visual features in intuitive physics judgments

Cognitive Science Society 2025, Wilma Alice Bainbridge, Kannon Bhattacharyya, Ren Calabro, Yuan Chang Leong

eScholarship (California Digital Library) · 18.06.2025

DOI: 10.48448/t4cw-kz03 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eScholarship (California Digital Library), erschienen am 18.06.2025. Verfasst von Cognitive Science Society 2025 und 4 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humans reliably infer complex physical relationships between objects in everyday scenes, yet the mechanisms underlying these judgments remain unclear. We explored whether convolutional neural networks (CNNs) can approximate intuitive physical reasoning by capturing statistical regularities in visual experience. We trained a CNN (Inception-v4) to predict tower stability and tested how well its outputs aligned with human judgments (N = 500). CNN predictions more closely matched human judgments (r = 0.718, p < 0.001, accuracy = 81%) than ground-truth predictions from physics simulations (r = 0.406, p = 0.002, accuracy = 68%), suggesting that both CNNs and humans rely on visual heuristics. Eye-tracking data revealed that CNN importance maps overlapped significantly with human gaze patterns, indicating shared attention to features statistically predictive of physical outcomes in intuitive physical judgments. Our findings show that CNNs trained on visual data capture perceptual cues used in human intuitive physics, highlighting their value as models of heuristic reasoning.

Schlagwörter

intuitive physicstower stabilityconvolutional neural networksvisual heuristicsgaze patternsattention mapsphysics simulationperceptual cuesheuristic reasoningInception-v4

Zitieren

APA

2025, C. S. S., Bainbridge, W. A., Bhattacharyya, K., Calabro, R., & Leong, Y. C. (2025). Humans and convolutional neural networks prioritize similar visual features in intuitive physics judgments. eScholarship (California Digital Library). https://doi.org/10.48448/t4cw-kz03

Vancouver

2025 CSS, Bainbridge WA, Bhattacharyya K, Calabro R, Leong YC. Humans and convolutional neural networks prioritize similar visual features in intuitive physics judgments. eScholarship (California Digital Library). 2025. doi:10.48448/t4cw-kz03

BibTeX
@article{2025,
  author = {2025, Cognitive Science Society and Bainbridge, Wilma Alice and Bhattacharyya, Kannon and Calabro, Ren and Leong, Yuan Chang},
  title = {Humans and convolutional neural networks prioritize similar visual features in intuitive physics judgments},
  journal = {eScholarship (California Digital Library)},
  year = {2025},
  doi = {10.48448/t4cw-kz03}
}
Kostenlos starten →