Name
Title | ||
|---|---|---|
Achieving robustness in classification using optimal transport with hinge regularization |
Abstract | ||
|---|---|---|
Adversarial examples have pointed out Deep Neural Network’s vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with classical loss functions. We propose a new framework for binary classification, based on optimal transport, which integrates this Lipschitz constraint as a theoretical requirement. ... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPR46437.2021.00057 | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Keywords | DocType | ISSN |
Computer vision,Computational modeling,Transportation,Estimation,Fasteners,Robustness,Pattern recognition | Conference | 1063-6919 |
ISBN | Citations | PageRank |
978-1-6654-4509-2 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mathieu Serrurier | 1 | 267 | 26.94 |
| Mamalet Franck | 2 | 0 | 0.34 |
| González-Sanz Alberto | 3 | 0 | 0.68 |
| Boissin Thibaut | 4 | 0 | 0.34 |
| Jean-Michel Loubes | 5 | 43 | 11.63 |
| Eustasio del Barrio | 6 | 2 | 3.16 |