HIVE: Evaluating the Human Interpretability of Visual Explanations. (arXiv:2112.03184v2 [cs.CV] UPDATED)

As machine learning is increasingly applied to high-impact, high-risk
domains, there have been a number of new methods aimed at making AI models more
human interpretable. Despite the recent growth of interpretability work, there
is a lack of systematic evaluation of proposed techniques. In this work, we
propose a novel human evaluation framework HIVE (Human Interpretability of
Visual Explanations) for diverse interpretability methods in computer vision;
to the best of our knowledge, this is the first work of its kind. …

arxiv cv human interpretability