SmoothGrad: removing noise by adding noise

DOI10.48550/ARXIV.1706.03825arXiv1706.03825MaRDI QIDQ87188

Nikhil Thorat, Martin Wattenberg, Daniel Smilkov, Fernanda Viégas, Been Kim

Publication date: 12 June 2017

Abstract: Explaining the output of a deep network remains a challenge. In the case of an image classifier, one type of explanation is to identify pixels that strongly influence the final decision. A starting point for this strategy is the gradient of the class score function with respect to the input image. This gradient can be interpreted as a sensitivity map, and there are several techniques that elaborate on this basic idea. This paper makes two contributions: it introduces SmoothGrad, a simple method that can help visually sharpen gradient-based sensitivity maps, and it discusses lessons in the visualization of these maps. We publish the code for our experiments and a website with our results.