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 language | English (US) |
|---|---|
| Title of host publication | Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 2798-2804 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781538610343 |
| DOIs | |
| State | Published - Jul 1 2017 |
| Event | 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy Duration: Oct 22 2017 → Oct 29 2017 |
Publication series
| Name | Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 |
|---|---|
| Volume | 2018-January |
Other
| Other | 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 |
|---|---|
| Country | Italy |
| City | Venice |
| Period | 10/22/17 → 10/29/17 |
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