Article

Human Sensitivity to Perturbations Constrained by a Model of the Natural Image Manifold

2018-05-11

Abstract excerpt

Humans are remarkably well tuned to the statistical properties of natural images. However, quantitative characterization of processing within the domain of natural images has been difficult because most parametric manipulations of a natural image make that image appear less natural. We used generative adversarial networks (GANs) to constrain parametric manipulations to remain within an approximation of the manifol...

Topics

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

Identifiers and source

Literature Corpus work: d8ba22eb-ecc6-5c69-b00b-48a3bae7bbf5
DOI: 10.1101/320531

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Human Sensitivity to Perturbations Constrained by a Model of the Natural Image ManifoldDOI 10.1101/320531Read

Contrast invariant tuning in human perception of image contentSemantic proximity Read

Probing Human Categorization of Naturalistic Images by Combining Deep Neural Networks with Cognitive ModelsSemantic proximity Read

What do adversarial images tell us about human vision?Semantic proximity Read

Scene wheels: Measuring perception and memory of real-world scenes with a continuous stimulus spaceSemantic proximity Read

An image-computable model of human visual shape similaritySemantic proximity Read

Human Latent Metrics: Perceptual and Cognitive Response Corresponds to Distance in GAN Latent SpaceSemantic proximity Read

Model metamers illuminate divergences between biological and artificial neural networksSemantic proximity Read

Robust deep learning object recognition models rely on low frequency information in natural imagesSemantic proximity Read

Constrained sampling from deep generative image models reveals mechanisms of human target detectionSemantic proximity Read

Enhancing Human Detection of Real and AI-Generated Hyperrealistic FacesSemantic proximity Read

Enhancing Human Detection of Real and AI-Generated Hyperrealistic FacesSemantic proximity Read

Making a scene – using GAN generated scenes to test the role of real-world co-occurence statistics and hierarchical feature spaces in scene understanding.Semantic proximity Read