Michal Irani

Natural and Adversarial Error Detection using Invariance to Image Transformations

2019 · arXiv (Cornell University)

We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur $\it{unintentionally}$ ("natural errors"), or due to $\it{intentional~adversarial~attacks}$ ("adversarial errors"), both in a single $\it{unified~framework}$. Our …