the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2017

    SmoothGrad: removing noise by adding noise

    Daniel Smilkov (first author) · 2017

    Read the original

    arXiv 1706.03825OpenAlex W2626639386

    On the reading lists

    Why it matters

    Introduced noise-averaged gradients, substantially improving the visual clarity of saliency explanations.

    Condensed from the expert lists' notes.

    The record

    First released
    2017 (from arXiv 1706.03825)
    Citations
    2,769 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.400 · computed rank 366 · consensus 0.55, must-read 0, citations percentile 0.67 (2010s · safety), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.