Sample-Centric Feature Generation for Semi-Supervised Few-Shot Learning

Semi-supervised few-shot learning aims to improve the model generalization ability by means of both limited labeled data and widely-available unlabeled data. Previous works attempt to model the relations between the few-shot labeled data and extra unlabeled data, by performing a label propagation or...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 04., Seite 2309-2320
1. Verfasser: Zhang, Bo (VerfasserIn)
Weitere Verfasser: Ye, Hancheng, Yu, Gang, Wang, Bin, Wu, Yike, Fan, Jiayuan, Chen, Tao
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