Hierarchical Prototype Refinement With Progressive Inter-Categorical Discrimination Maximization for Few-Shot Learning

Metric-based few-shot learning categorizes unseen query instances by measuring their distance to the categories appearing in the given support set. To facilitate distance measurement, prototypes are used to approximate the representations of categories. However, we find prototypical representations...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 01., Seite 3414-3429
Auteur principal: Zhou, Yuan (Auteur)
Autres auteurs: Guo, Yanrong, Hao, Shijie, Hong, Richang
Format: Article en ligne
Langue:English
Publié: 2022
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article