Dataset similarity to assess semi-supervised learning under distribution mismatch between the labelled and unlabelled datasets

HIGHLIGHTS

• who: Labelled et al. from the Institute, MMolina-Cabello and E. Lu00f3pez-Rubio are with the University of Mu00e1laga have published the Article: Dataset Similarity to Assess Semi-supervised Learning Under Distribution Mismatch Between the Labelled and Unlabelled Datasets, in the Journal: (JOURNAL) of June/22,/2021
• what: The authors propose a quantitative dataset selection heuristic based on dataset dissimilarity measures. The authors assess the impact of distribution mismatches on the outcomes of the semi-supervised MixMatch algorithm. The authors demonstrate that including OOD data in the unlabelled training dataset for the MixMatch algorithm can . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.