Learning by Seeing More Classes

Traditional pattern recognition models usually assume a fixed and identical number of classes during both training and inference stages. In this paper, we study an interesting but ignored question: can increasing the number of classes during training improve the generalization and reliability perfor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 6 vom: 20. Juni, Seite 7477-7493
1. Verfasser:	Zhu, Fei (VerfasserIn)
Weitere Verfasser:	Zhang, Xu-Yao, Wang, Rui-Qi, Liu, Cheng-Lin
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2023
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article