Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

1 code implementation • arXiv 2020 • Gary S. W. Goh, Sebastian Lapuschkin, Leander Weber, Wojciech Samek, Alexander Binder

From our experiments, we find that the SmoothTaylor approach together with adaptive noising is able to generate better quality saliency maps with lesser noise and higher sensitivity to the relevant points in the input space as compared to Integrated Gradients.

Image Classification Object Recognition