Search Results for author:
Found 3 papers, 2 papers with code
Generalized Adversarial Distances to Efficiently Discover Classifier Errors
In this paper we propose a generalization to the Adversarial Distance search that leverages concepts from adversarial machine learning to identify predictions for which a classifier may be overly confident.
Harnessing Adversarial Distances to Discover High-Confidence Errors
Through rigorous empirical experimentation, we demonstrate that our Adversarial Distance search discovers high-confidence errors at a rate greater than expected given model confidence.
Facility Locations Utility for Uncovering Classifier Overconfidence
Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
