Generating corner cases for crashtesting deep networks
Résumé
Today, adversarial attack is almost the only kind of hard samples considered by the community to tickle deep networks.
However, such additive perturbations are not realistic for many applications (e.g. remote sensing).
This paper introduce a new kind of hard samples called corner cases where the entire data is generated (not just a perturbation). This allows to constraint more easily those data to be both hard but also realistic.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...