Back to search

Article

An image-computable model of human visual shape similarity

2020-01-11

Abstract excerpt

Shape is a defining feature of objects. Yet, no image-computable model accurately predicts how similar or different shapes appear to human observers. To address this, we developed a model (‘ShapeComp’), based on over 100 shape features (e.g., area, compactness, Fourier descriptors). When trained to capture the variance in a database of >25,000 animal silhouettes, ShapeComp predicts human shape similarity judgments...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
7c6caa50-6730-52f5-98d6-602213051abb
DOI
10.1101/2020.01.10.901876
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
An image-computable model of human visual shape similarityDOI 10.1101/2020.01.10.901876
Creating Perceptually Uniform Circular Shape Spaces: An Automated Method for Asymmetric Naturalistic ShapesSemantic proximity
Automated Generation of Perceptually-Uniform Circular Spaces for Novel Naturalistic ShapesSemantic proximity
The Oomplet Dataset Toolkit: A flexible and extensible system for large-scale, multi-category image generationSemantic proximity
Probing Human Categorization of Naturalistic Images by Combining Deep Neural Networks with Cognitive ModelsSemantic proximity
From visual appearance to material categoriesSemantic proximity
From visual appearance to material categoriesSemantic proximity
Scene wheels: Measuring perception and memory of real-world scenes with a continuous stimulus spaceSemantic proximity
Contrast invariant tuning in human perception of image contentSemantic proximity
Human Sensitivity to Perturbations Constrained by a Model of the Natural Image ManifoldSemantic proximity
Revealing the multidimensional mental representations of natural objects underlying human similarity judgmentsSemantic proximity
Teaching deep networks to see shape: Lessons from a simplified visual worldSemantic proximity
Face dissimilarity judgements are predicted by representational distance in morphable and image-computable modelsSemantic proximity
Select a neighboring publication to make it the new centre.