Prediction Consistency Regularization for Learning with Noise Labels Based on Contrastive Clustering

In the classification task, label noise has a significant impact on models’ performance, primarily manifested in the disruption of prediction consistency, thereby reducing the classification accuracy. This work introduces a novel prediction consistency regularization that mitigates the impact of lab...

Olles dieđut

Bibliográfalaš dieđut

Váldodahkkit:	Xinkai Sun, Sanguo Zhang, Shuangge Ma
Materiálatiipa:	Artigo
Giella:	Inglês
Almmustuhtton:	MDPI AG 2024-03-01
Ráidu:	Entropy
Fáttát:	deep learning noisy label consistency regularization contrastive learning
Liŋkkat:	https://www.mdpi.com/1099-4300/26/4/308
Fáddágilkorat:	Lasit fáddágilkoriid Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!