A Case for Soft Loss Functions

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

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


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.
Original languageEnglish
Title of host publicationProceedings of the eighth AAAI Conference on Human Computation and Crowdsourcing
PublisherAAAI Press
Publication date2020
Publication statusPublished - 2020


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


Dive into the research topics of 'A Case for Soft Loss Functions'. Together they form a unique fingerprint.

Cite this