Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Representational similarity analysis-connecting the branches of systems neuroscience
Kriegeskorte, N. (2008) · Frontiers in Systems Neuroscience · doi:10.3389/neuro.06.004.2008 · Cited by 3,355
The Diffusion Decision Model: Theory and Data for Two-Choice Decision Tasks
Ratcliff, R., & McKoon, G. (2008) · Neural Computation · doi:10.1162/neco.2008.12-06-420 · Cited by 3,059
Understanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 1×
“Nonethe-less, large overparameterized neural networks like Inception have the capacity to learn the shuffled-pixel training set, although they will not generalize to new examples (Zhang et al. 2016).”
BackgroundSelf-citationSelf-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
Daselaar, S. M. (2009) · Frontiers in Human Neuroscience · doi:10.3389/neuro.09.013.2009 · Cited by 1,501
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Bau, D., Zhou, B., Khosla, A., Oliva, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.354 · Cited by 1,389
Cited by
Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
Kim, S. S. Y., Watkins, E. A., Russakovsky, O., Fong, R., & Monroy-Hernández, A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581001 · Cited by 233
Deep problems with neural network models of human vision
Bowers, J. S., Malhotra, G., Dujmović, M., Llera Montero, M., Tsvetkov, C., Biscione, V., Puebla, G., Adolfi, F., Hummel, J. E., Heaton, R. F., et al. (2023) · Behavioral and Brain Sciences · doi:10.1017/s0140525x22002813 · Cited by 204
Partial success in closing the gap between human and machine vision
Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2021) · arXiv · doi:10.48550/arxiv.2106.07411 · Cited by 129
HIVE: Evaluating the Human Interpretability of Visual Explanations
Kim, S. S. Y., Meister, N., Ramaswamy, V. V., Fong, R., & Russakovsky, O. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19775-8_17 · Cited by 72
Predictive coding feedback results in perceived illusory contours in a recurrent neural network
Pang, Z., O’May, C. B., Choksi, B., & VanRullen, R. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.08.024 · Cited by 44
Metadata
- Authors
- Kim, B., Reif, E., Wattenberg, M., Bengio, S., & Mozer, M. C.
- Venue
- Computational Brain & Behavior
- Published
- 2021-04-09
- Volume
- 4
- Issue
- 3
- Pages
- 251-263
- ISSN
- 2522-0861 (ISSN-L)
- 2522-087X
- OpenAlex
- W3153606705
- Cited by
- 43
- References
- 14
- FWCI
- 4.03
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure. https://app.cochat.ai/papers/10.1007/s42113-021-00100-7
- The paper
- Kim, B., Reif, E., Wattenberg, M., Bengio, S., & Mozer, M. C. (2021). Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure. Computational Brain & Behavior. https://doi.org/10.1007/s42113-021-00100-7
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.