Article

What do adversarial images tell us about human vision?

2020-02-26

Abstract excerpt

Deep convolutional neural networks (DCNNs) are frequently described as promising models of human and primate vision. An obvious challenge to this claim is the existence of adversarial images that fool DCNNs but are uninterpretable to humans. However, recent research has suggested that there may be similarities in how humans and DCNNs interpret these seemingly nonsense images. In this study, we reanalysed data fro...

Topics

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

Identifiers and source

Literature Corpus work: d9201a48-afbd-521e-8a8c-e22558ce70d1
DOI: 10.1101/2020.02.25.964361

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

What do adversarial images tell us about human vision?DOI 10.1101/2020.02.25.964361Read

Generation and Countermeasures of Adversarial Examples on Vision: A SurveySemantic proximity Read

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

Human Sensitivity to Perturbations Constrained by a Model of the Natural Image ManifoldSemantic proximity Read

Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image PerturbationsSemantic 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

Optimally Configured Generative Adversarial Networks to Distinguish Real and AI- Generated Human FacesSemantic proximity Read

Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks With Transfer LearningSemantic proximity Read

Classifying Real and AI-Generated Images Using Fine-Tuned ResNet50.Semantic proximity Read

Photo-Synthesis: Attributed controlled sketch to image translation using Generative Adversarial Networks for assisting criminal identificationSemantic proximity Read

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

Beyond AI: Fooling DNN Model in Physical WorldSemantic proximity Read