Noise increases the correspondence between artificial and human vision

Jessica A F Thompson

PLOS Biology, 2021, vol. 19, issue 12, 1-4

Abstract: The best performing computer vision systems are based on deep neural networks (DNNs). A study in this issue of PLOS Biology shows that DNNs trained on noisy stimuli are better than standard DNNs at mirroring both human behavioral and neural visual responses.This Primer explores the implications of a recent PLOS Biology study, arguing that noise-robustness, a property of human vision that standard computer vision models fail to mimic, provides an opportunity to probe the neural mechanisms underlying visual object recognition and refine computational models of the ventral visual stream.

Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3001477 (text/html)
https://journals.plos.org/plosbiology/article/file ... 01477&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pbio00:3001477

DOI: 10.1371/journal.pbio.3001477

Access Statistics for this article

More articles in PLOS Biology from Public Library of Science
Bibliographic data for series maintained by plosbiology ().