Generalized Adversarial Distances to Efficiently Discover Classifier Errors

1 code implementation • 25 Feb 2021 • Walter Bennette, Sally Dufek, Karsten Maurer, Sean Sisti, Bunyod Tusmatov

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

1 code implementation • 29 Jun 2020 • Walter Bennette, Karsten Maurer, Sean Sisti

Through rigorous empirical experimentation, we demonstrate that our Adversarial Distance search discovers high-confidence errors at a rate greater than expected given model confidence.

Image Classification Vocal Bursts Intensity Prediction