A Fourier Perspective on Model Robustness in Computer Vision

Raphael Gontijo Lopes
Raphael Gontijo Lopes
Justin Gilmer
Justin Gilmer

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 13255-13265, 2019.

Cited by: 51|Bibtex|Views147
EI
Other Links: dblp.uni-trier.de|arxiv.org

Abstract:

Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is often met with reduced ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments