Rebalanced Zero-Shot Learning

Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer unseen classes. However, we find that such existing models mo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 19., Seite 4185-4198
1. Verfasser:	Ye, Zihan (VerfasserIn)
Weitere Verfasser:	Yang, Guanyu, Jin, Xiaobo, Liu, Youfa, Huang, Kaizhu
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2023
Zugriff auf das übergeordnete Werk:	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:	Journal Article