Can the early human visual system compete with deep neural networks?

Samuel Dodge, Lina Karam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

We study and compare the human visual system and state-of-The-Art deep neural networks on classification of distorted images. Different from previous works, we limit the display time to 100ms to test only the early mechanisms of the human visual system, without allowing time for any eye movements or other higher level processes. Our findings show that the human visual system still outperforms modern deep neural networks under blurry and noisy images. These findings motivate future research into developing more robust deep networks.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2798-2804
Number of pages7
ISBN (Electronic)9781538610343
DOIs
StatePublished - Jul 1 2017
Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
Duration: Oct 22 2017Oct 29 2017

Publication series

NameProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Volume2018-January

Other

Other16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
CountryItaly
CityVenice
Period10/22/1710/29/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Can the early human visual system compete with deep neural networks?'. Together they form a unique fingerprint.

  • Cite this

    Dodge, S., & Karam, L. (2017). Can the early human visual system compete with deep neural networks? In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 (pp. 2798-2804). (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2017.329