GAN-CL: Generative Adversarial Networks for Learning From Complementary Labels

Learning from complementary labels (CLs) is a useful learning paradigm, where the CL specifies the classes that the instance does not belong to, instead of providing the ground truth as in the ordinary supervised learning scenario. In general, although it is less laborious and more efficient to coll...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on cybernetics 2023-01, Vol.53 (1), p.236-247
Hauptverfasser:	Liu, Jiabin, Hang, Hanyuan, Wang, Bo, Li, Biao, Wang, Huadong, Tian, Yingjie, Shi, Yong
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Classifiers Complementary label (CL) learning Discriminators Economics Generative adversarial networks generative adversarial networks (GANs) Generators Labels Supervised learning Task analysis Training Training data weakly supervised learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!