Evaluating Layer-wise Relevance Propagation Explainability Maps for Artificial Neural Networks

摘要

Layer-wise relevance propagation (LRP) heatmaps aim to provide graphical explanation for decisions of a classifier. This could be of great benefit to scientists for trusting complex black-box models and getting insights from their data. The LRP heatmaps tested on benchmark datasets are reported to correlate significantly with interpretable image features. In this work, we investigate these claims and propose to refine them.