research
∙
02/25/2021
Generalized Adversarial Distances to Efficiently Discover Classifier Errors
Given a black-box classification model and an unlabeled evaluation datas...
research
∙
06/29/2020
Harnessing Adversarial Distances to Discover High-Confidence Errors
Given a deep neural network image classification model that we treat as ...
research
∙
10/12/2018