the open
    research
    Contribute
    Back to the reading lists

    Computer vision & multimodal· 2008

    Extracting and composing robust features with denoising autoencoders

    Pascal Vincent (first author) · 2008

    Read the original

    DOI 10.1145/1390156.1390294OpenAlex W2025768430

    On the reading lists

    Why it matters

    Established input corruption and reconstruction as powerful objectives for unsupervised feature learning.

    Condensed from the expert lists' notes.

    The record

    First released
    2008 (from OpenAlex)
    Citations
    7,436 citations, as counted by OpenAlex (CC0)
    Named by
    both expert lists
    Score
    0.328 · computed rank 537 · consensus 0.51, must-read 0, citations percentile 0.5 (2000s · vision), 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.