the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2013

    Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

    Karen Simonyan (first author) · 2013

    Read the original

    arXiv 1312.6034OpenAlex W2169393322

    On the reading lists

    Why it matters

    Established gradient-based saliency maps as a foundational technique for understanding image classifiers.

    Condensed from the expert lists' notes.

    The record

    First released
    2013 (from arXiv 1312.6034)
    Citations
    8,625 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.584 · computed rank 166 · consensus 0.8, must-read 0.5, citations percentile 0.84 (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.