Are Deep Neural Networks "Robust"?
Author:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- A New Approach to Robust Estimation of Parametric StructuresIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Is Robustness the Cost of Accuracy? – A Comprehensive Study on the Robustness of 18 Deep Image Classification Models2018
- Deep Hierarchies in the Primate Visual Cortex: What Can We Learn for Computer Vision?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- A survey of robust statisticsStatistical Methods & Applications, 2007
- A History of Parametric Statistical Inference from Bernoulli to Fisher, 1713–19352007
- Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography1987