Papers › SmoothGrad: removing noise by adding noise

SmoothGrad: removing noise by adding noise

12 Jun 2017arXiv:1706.03825archive 2025-07-28

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

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

20 repositories listed; official and paper-mentioned ones first.

PAIR-code/saliency officialmentioned on GitHubtf report
TooTouch/WhiteBox-Part1 mentioned on GitHubpytorch report
ascillitoe/shap mentioned on GitHubtf report
austinbrown34/shap mentioned on GitHubtf report
bips-hb/innsight mentioned on GitHubtorch report
gablabc/shap mentioned on GitHubtf report
hs2k/pytorch-smoothgrad mentioned on GitHubpytorch report
idiap/fullgrad-saliency mentioned on GitHubpytorch report
koren-v/Interpret mentioned on GitHubpytorch report
miaolan-xie/shap mentioned on GitHubtf report
pytorch/captum mentioned on GitHubpytorchBSD-3-Clause report
saivarunr/xshap mentioned on GitHubtf report
sar-gupta/convisualize_nb mentioned on GitHubpytorch report
shaoshanglqy/shap-shapley mentioned on GitHubtf report
shap/shap mentioned on GitHubtf report
sicara/tf-explain mentioned on GitHubtf report
slundberg/shap mentioned on GitHubtfMIT report
vlue-c/PyTorch-Explanations mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Interpretable Machine LearningSensitivity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections