Transforming gradient-based techniques into interpretable methods

Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman

Abstract: Highlights•We propose GAD method to simplify explanations, providing easy-to-interpret maps.•Our gradient-based method focuses on revealing feature importance in CNNs.•GAD minimizes noise in explanations compared to usual gradient-based techniques.•Class distinction is enhanced thanks to our method.•Empirical results show that GAD locates decisive image areas for classification.