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

Samuel Dodge, Lina Karam

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

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
Volume2018-January
ISBN (Electronic)9781538610343
DOIs
StatePublished - Jan 19 2018
Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
Duration: Oct 22 2017 → Oct 29 2017

Other

Other16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
CountryItaly
CityVenice
Period10/22/17 → 10/29/17

Fingerprint

Eye movements
Display devices
Deep neural networks

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

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

Can the early human visual system compete with deep neural networks? / Dodge, Samuel; Karam, Lina.

Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 2798-2804.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Dodge, S & Karam, L 2018, Can the early human visual system compete with deep neural networks? in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 2798-2804, 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Venice, Italy, 10/22/17. https://doi.org/10.1109/ICCVW.2017.329
Dodge S, Karam L. Can the early human visual system compete with deep neural networks? In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 2798-2804 https://doi.org/10.1109/ICCVW.2017.329
Dodge, Samuel ; Karam, Lina. / Can the early human visual system compete with deep neural networks?. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 2798-2804
@inproceedings{c0040393cc014548b43b9bb6b0ece10f,
title = "Can the early human visual system compete with deep neural networks?",
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.",
author = "Samuel Dodge and Lina Karam",
year = "2018",
month = "1",
day = "19",
doi = "10.1109/ICCVW.2017.329",
language = "English (US)",
volume = "2018-January",
pages = "2798--2804",
booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Can the early human visual system compete with deep neural networks?

AU - Dodge, Samuel

AU - Karam, Lina

PY - 2018/1/19

Y1 - 2018/1/19

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85046287206&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046287206&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2017.329

DO - 10.1109/ICCVW.2017.329

M3 - Conference contribution

VL - 2018-January

SP - 2798

EP - 2804

BT - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Access to Document