Are Deep Neural Networks "Robust"?
arXiv:2008.12650v1
Originality Synthesis-oriented
AI Analysis
This is an incremental analysis that critiques the robustness of deep neural networks for researchers in computer vision and machine learning.
The paper argues that deep neural networks do not meet the traditional definition of robustness in computer vision, which involves separating outliers from inliers, and concludes they are not robust by this standard.
Separating outliers from inliers is the definition of robustness in computer vision. This essay delineates how deep neural networks are different than typical robust estimators. Deep neural networks not robust by this traditional definition.