Redundant features can hurt robustness to distributions shift

2020.

Cited by: 0|Bibtex|Views5

Abstract:

In this work, we borrow tools from the field of adversarial robustness, and propose a new framework that permits to relate dataset features to the distance of samples to the decision boundary. Using this framework we identify the subspace of features used by CNNs to classify largescale vision benchmarks, and reveal some intriguing aspects...More

Code:

Data:

Your rating :
0

 

Tags
Comments