Can the Early Human Visual System Compete with Deep Neural Networks?

ICCVW 2017 pp. 2798-2804

doi:10.1109/ICCVW.2017.329 /iccvw/2017/dodge2017iccvw-early/

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.

PDF ICCVW Semantic Scholar

Cite

Text

Dodge and Karam. "Can the Early Human Visual System Compete with Deep Neural Networks?." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.329

Markdown

[Dodge and Karam. "Can the Early Human Visual System Compete with Deep Neural Networks?." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/dodge2017iccvw-early/) doi:10.1109/ICCVW.2017.329

BibTeX

@inproceedings{dodge2017iccvw-early,
  title     = {{Can the Early Human Visual System Compete with Deep Neural Networks?}},
  author    = {Dodge, Samuel Fuller and Karam, Lina J.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {2798-2804},
  doi       = {10.1109/ICCVW.2017.329},
  url       = {https://mlanthology.org/iccvw/2017/dodge2017iccvw-early/}
}