A Case for Soft Loss Functions

Alexandra Uma, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, Barbara Plank, Massimo Poesio

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

    Abstract

    Recently, Peterson et al. provided evidence of the benefits of using probabilistic soft labels generated from crowd annotations for training a computer vision model, showing that us- ing such labels maximizes performance of the models over unseen data. In this paper, we generalize these results by showing that training with soft labels is an effective method for using crowd annotations in several other AI tasks besides the one studied by Peterson et al., and also when their performance is compared with that of state-of-the-art methods for learning from crowdsourced data.
    OriginalsprogEngelsk
    TitelProceedings of the eighth AAAI Conference on Human Computation and Crowdsourcing
    ForlagAAAI Press
    Publikationsdato2020
    StatusUdgivet - 2020

    Emneord

    • Probabilistic soft labels
    • Crowd annotations
    • Computer vision model
    • AI tasks
    • Crowdsourced data

    Fingeraftryk

    Dyk ned i forskningsemnerne om 'A Case for Soft Loss Functions'. Sammen danner de et unikt fingeraftryk.

    Citationsformater