Translations:Transfer Learning/11/en: Difference between revisions

    From Marovi AI
    (Importing a new version from external source)
    Tag: Manual revert
    (Importing a new version from external source)
    Tag: Manual revert
     
    Line 5: Line 5:
    | '''Feature extraction''' || Freeze all pretrained layers; train only a new output head || Very small target dataset; source and target are closely related
    | '''Feature extraction''' || Freeze all pretrained layers; train only a new output head || Very small target dataset; source and target are closely related
    |-
    |-
    | '''Fine-tuning (full)''' || Unfreeze all layers and train end-to-end with a small learning rate || Moderate target dataset; source and target differ meaningfully
    | '''{{Term|fine-tuning}} (full)''' || Unfreeze all layers and train end-to-end with a small {{Term|learning rate}} || Moderate target dataset; source and target differ meaningfully
    |-
    |-
    | '''Gradual unfreezing''' || Progressively unfreeze layers from top to bottom over training || Balances stability of lower features with adaptation of higher ones
    | '''Gradual unfreezing''' || Progressively unfreeze layers from top to bottom over training || Balances stability of lower features with adaptation of higher ones
    |}
    |}

    Latest revision as of 23:34, 27 April 2026

    Information about message (contribute)
    This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.
    Message definition (Transfer Learning)
    {| class="wikitable"
    |-
    ! Strategy !! Description !! When to use
    |-
    | '''Feature extraction''' || Freeze all pretrained layers; train only a new output head || Very small target dataset; source and target are closely related
    |-
    | '''{{Term|fine-tuning}} (full)''' || Unfreeze all layers and train end-to-end with a small {{Term|learning rate}} || Moderate target dataset; source and target differ meaningfully
    |-
    | '''Gradual unfreezing''' || Progressively unfreeze layers from top to bottom over training || Balances stability of lower features with adaptation of higher ones
    |}
    Strategy Description When to use
    Feature extraction Freeze all pretrained layers; train only a new output head Very small target dataset; source and target are closely related
    fine-tuning (full) Unfreeze all layers and train end-to-end with a small learning rate Moderate target dataset; source and target differ meaningfully
    Gradual unfreezing Progressively unfreeze layers from top to bottom over training Balances stability of lower features with adaptation of higher ones
    Retrieved from "https://marovi.ai/index.php?title=Translations:Transfer_Learning/11/en&oldid=17628"