Pith. sign in

REVIEW 2 cited by

Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1903.01069 v4 pith:ZRWPYOHZ submitted 2019-03-04 cs.LG stat.ML

classification cs.LGstat.ML
keywords closuregestaltnaturalelementshumaninterpretedlawsneural
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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 despite their ecological validity. We use deep-learning methods to investigate whether natural scene statistics might be sufficient to derive the Gestalt laws. 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 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    IllusionBench+ is a 1,051-image benchmark with 5,548 QA pairs and golden descriptions for testing vision-language models on classic, real-scene, Ishihara, and trap visual illusions, and it finds top models such as GPT...

  2. The Art of Deception: Color Visual Illusions and Diffusion Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    DDIM inversion in diffusion models produces brightness and color shifts that track human visual illusions, and a diffusion-based optimizer can generate new illusions in realistic images that fool human observers.

Pith tools