25 citations · 53 across the 4 of their papers we have counts for
4 papers
Quantifying and mitigating the impact of label errors on model disparity metrics
Julius Adebayo, Melissa Hall, Bowen Yu +1
Errors in labels obtained via human annotation adversely affect a model's performance. Existing approaches propose ways to mitigate the effect of label error on a model's downstrea…
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation
Julius Adebayo, Michael Muelly, Hal Abelson +1
We investigate whether three types of post hoc model explanations--feature attribution, concept activation, and training point ranking--are effective for detecting a model's relian…
Debugging Tests for Model Explanations
Julius Adebayo, Michael Muelly, Ilaria Liccardi +1
We investigate whether post-hoc model explanations are effective for diagnosing model errors--model debugging. In response to the challenge of explaining a model's prediction, a va…
Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imaging
Nishanth Arun, Nathan Gaw, Praveer Singh +10
Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most…