Using Videos to Evaluate Image Model Robustness

Keren Gu
Keren Gu
Brandon Yang
Brandon Yang

arXiv: Computer Vision and Pattern Recognition, 2019.

Cited by: 8|Bibtex|Views139
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Human visual systems are robust to a wide range of image transformations that are challenging for artificial networks. We present the first study of image model robustness to the minute transformations found across video frames, which we term Compared to previous studies on adversarial examples and synthetic distortions, natural robustn...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments