Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure
Open Access
- 9 April 2021
- journal article
- research article
- Published by Springer Nature in Computational Brain & Behavior
- Vol. 4 (3) , 251-263
Abstract
The Gestalt laws of perceptual organization, which describe how visual elements in an image are grouped and interpreted, have traditionally been thought of as innate. Given past research showing that these laws have ecological validity, we investigate whether deep learning methods infer Gestalt laws from the statistics of natural scenes. We examine the law of closure, which asserts that human visual perception tends to “close the gap” by assembling elements that can jointly be interpreted as a complete figure or object. We demonstrate that a state-of-the-art convolutional neural network, trained to classify natural images, exhibits closure on synthetic displays of edge fragments, as assessed by similarity of internal representations. This finding provides further support for the hypothesis that the human perceptual system is even more elegant than the Gestaltists imagined: a single law—adaptation to the statistical structure of the environment—might suffice as fundamental.Keywords
All Related Versions
This publication has 42 references indexed in Scilit:
- A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure–ground organization.Psychological Bulletin, 2012
- Natural-Scene Statistics Predict How the Figure–Ground Cue of Convexity Affects Human Depth PerceptionThe Journal of Neuroscience, 2010
- The Diffusion Decision Model: Theory and Data for Two-Choice Decision TasksNeural Computation, 2008
- Gestalt principlesScholarpedia, 2008
- Ecological statistics of Gestalt laws for the perceptual organization of contoursJournal of Vision, 2002
- Art, Design and Gestalt TheoryLeonardo, 1998
- The Role of Wholistic/Configural Properties versus Global Properties in Visual Form PerceptionPerception, 1994
- Primacy of wholistic processing and global/local paradigm: A critical review.Psychological Bulletin, 1992
- Perceptual organization and focused attention: The role of objects and proximity in visual processingPerception & Psychophysics, 1991
- Search for "closure" in a visually perceived pattern.Psychological Bulletin, 1968