ImageNet-trained deep neural networks exhibit illusion-like response to the Scintillating grid
| Autor: | Ron Dekel, Eric D. Sun |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
media_common.quotation_subject Illusion Luminance Article computer vision Scintillating grid illusion Humans Representation (mathematics) media_common Artificial neural network Contextual image classification business.industry Optical illusion deep neural network Cognitive neuroscience of visual object recognition Pattern recognition Grid Illusions Sensory Systems visual illusion Ophthalmology Visual Perception Neural Networks Computer Artificial intelligence business |
| Zdroj: | Journal of Vision |
| ISSN: | 1534-7362 |
| DOI: | 10.1167/jov.21.11.15 |
| Popis: | Deep neural network (DNN) models for computer vision are capable of human-level object recognition. Consequently, similarities between DNN and human vision are of interest. Here, we characterize DNN representations of Scintillating grid visual illusion images in which white disks are perceived to be partially black. Specifically, we use VGG-19 and ResNet-101 DNN models that were trained for image classification and consider the representational dissimilarity (\(L^1\) distance in the penultimate layer) between pairs of images: one with white Scintillating grid disks and the other with disks of decreasing luminance levels. Results showed a nonmonotonic relation, such that decreasing disk luminance led to an increase and subsequently a decrease in representational dissimilarity. That is, the Scintillating grid image with white disks was closer, in terms of the representation, to images with black disks than images with gray disks. In control nonillusion images, such nonmonotonicity was rare. These results suggest that nonmonotonicity in a deep computational representation is a potential test for illusion-like response geometry in DNN models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|