EID-GAN: Generative Adversarial Nets for Extremely Imbalanced Data Augmentation

Imbalanced data cause deep neural networks to output biased results, and it becomes more serious when facing extremely imbalanced data regarding the outliers with tiny size (the ratio of the outlier size to the image size is around 0.05%). Many data argumentation models are proposed to supplement im...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on industrial informatics 2023-03, Vol.19 (3), p.3208-3218
Hauptverfasser:	Li, Wei, Chen, Jinlin, Cao, Jiannong, Ma, Chao, Wang, Jia, Cui, Xiaohui, Chen, Ping
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Back propagation Back propagation networks Data augmentation Data models Datasets Detectors Extremely imbalanced data augmentation Fabrics generated data evaluation generative adversarial net (GAN) Generative adversarial networks Generators norm penalty function Outliers (statistics) Penalty function Pistons Prototypes Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!