the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2015

    Learning Deep Features for Discriminative Localization

    Bolei Zhou (first author) · 2015 · published 2016

    Read the original

    DOI 10.1109/cvpr.2016.319arXiv 1512.04150OpenAlex W2295107390

    On the reading lists

    Why it matters

    Introduced class activation maps, laying the groundwork for modern CNN localization explanations.

    Condensed from the expert lists' notes.

    The record

    First released
    2015 (from arXiv 1512.04150)
    Published
    2016
    Citations
    11,337 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.523 · computed rank 210 · consensus 0.69, must-read 0, citations percentile 0.904 (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.