A study and comparison of human and deep learning recognition performance under visual distortions

Samuel Dodge; Lina Karam

doi:10.1109/ICCCN.2017.8038465

A study and comparison of human and deep learning recognition performance under visual distortions

Samuel Dodge, Lina Karam

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

247 Scopus citations

Abstract

Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still much lower than human performance on distorted images. We additionally find that there is little correlation in errors between DNNs and human subjects. This could be an indication that the internal representation of images are different between DNNs and the human visual system. These comparisons with human performance could be used to guide future development of more robust DNNs.

Original language	English (US)
Title of host publication	2017 26th International Conference on Computer Communications and Networks, ICCCN 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509029914
DOIs	https://doi.org/10.1109/ICCCN.2017.8038465
State	Published - Sep 14 2017
Event	26th International Conference on Computer Communications and Networks, ICCCN 2017 - Vancouver, Canada Duration: Jul 31 2017 → Aug 3 2017

Other

Other	26th International Conference on Computer Communications and Networks, ICCCN 2017
Country/Territory	Canada
City	Vancouver
Period	7/31/17 → 8/3/17

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Software
Management of Technology and Innovation
Information Systems and Management
Safety, Risk, Reliability and Quality
Media Technology
Control and Optimization

Access to Document

10.1109/ICCCN.2017.8038465

Cite this

A study and comparison of human and deep learning recognition performance under visual distortions. / Dodge, Samuel; Karam, Lina.
2017 26th International Conference on Computer Communications and Networks, ICCCN 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 8038465.

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

Dodge, S & Karam, L 2017, A study and comparison of human and deep learning recognition performance under visual distortions. in 2017 26th International Conference on Computer Communications and Networks, ICCCN 2017., 8038465, Institute of Electrical and Electronics Engineers Inc., 26th International Conference on Computer Communications and Networks, ICCCN 2017, Vancouver, Canada, 7/31/17. https://doi.org/10.1109/ICCCN.2017.8038465

@inproceedings{3fc6bf0c133f43dea16b0845e14f3c39,

title = "A study and comparison of human and deep learning recognition performance under visual distortions",

abstract = "Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still much lower than human performance on distorted images. We additionally find that there is little correlation in errors between DNNs and human subjects. This could be an indication that the internal representation of images are different between DNNs and the human visual system. These comparisons with human performance could be used to guide future development of more robust DNNs.",

author = "Samuel Dodge and Lina Karam",

year = "2017",

month = sep,

day = "14",

doi = "10.1109/ICCCN.2017.8038465",

language = "English (US)",

booktitle = "2017 26th International Conference on Computer Communications and Networks, ICCCN 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "26th International Conference on Computer Communications and Networks, ICCCN 2017 ; Conference date: 31-07-2017 Through 03-08-2017",

}

TY - GEN

T1 - A study and comparison of human and deep learning recognition performance under visual distortions

AU - Dodge, Samuel

AU - Karam, Lina

PY - 2017/9/14

Y1 - 2017/9/14

N2 - Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still much lower than human performance on distorted images. We additionally find that there is little correlation in errors between DNNs and human subjects. This could be an indication that the internal representation of images are different between DNNs and the human visual system. These comparisons with human performance could be used to guide future development of more robust DNNs.

AB - Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still much lower than human performance on distorted images. We additionally find that there is little correlation in errors between DNNs and human subjects. This could be an indication that the internal representation of images are different between DNNs and the human visual system. These comparisons with human performance could be used to guide future development of more robust DNNs.

UR - http://www.scopus.com/inward/record.url?scp=85032266305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032266305&partnerID=8YFLogxK

U2 - 10.1109/ICCCN.2017.8038465

DO - 10.1109/ICCCN.2017.8038465

M3 - Conference contribution

AN - SCOPUS:85032266305

BT - 2017 26th International Conference on Computer Communications and Networks, ICCCN 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th International Conference on Computer Communications and Networks, ICCCN 2017

Y2 - 31 July 2017 through 3 August 2017

ER -

A study and comparison of human and deep learning recognition performance under visual distortions

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this