Physical Sciences and Mathematics Commons^™

Explainabilityaudit: An Automated Evaluation Of Local Explainability In Rooftop Image Classification, Duleep Rathgamage Don, Jonathan Boardman, Sudhashree Sayenju, Ramazan Aygun, Yifan Zhang, Bill Franks, Sereres Johnston, George Lee, Dan Sullivan, Girish Modgil

Published and Grey Literature from PhD Candidates

Explainable Artificial Intelligence (XAI) is a key concept in building trustworthy machine learning models. Local explainability methods seek to provide explanations for individual predictions. Usually, humans must check these explanations manually. When large numbers of predictions are being made, this approach does not scale. We address this deficiency for a rooftop classification problem specifically with ExplainabilityAudit, a method that automatically evaluates explanations generated by a local explainability toolkit and identifies rooftop images that require further auditing by a human expert. The proposed method utilizes explanations generated by the Local Interpretable Model-Agnostic Explanations (LIME) framework as the most important superpixels of …