ResLT: Residual Learning for Long-Tailed Recognition

Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the problem from either the aspect of input space (re-sampling classes with different frequencies) or loss space (re-weighting cla...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2023-03, Vol.45 (3), p.3695-3706
Hauptverfasser:	Cui, Jiequan, Liu, Shu, Tian, Zhuotao, Zhong, Zhisheng, Jia, Jiaya
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Deep learning Head Image enhancement Image recognition imbalanced learning long-tailed recognition Machine learning Magnetic heads Optimization Representation learning Residual learning Tail Training Transfer learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!