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...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 01., Seite 3414-3429
1. Verfasser: Zhou, Yuan (VerfasserIn)
Weitere Verfasser: Guo, Yanrong, Hao, Shijie, Hong, Richang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article