BPT-PLR: A Balanced Partitioning and Training Framework with Pseudo-Label Relaxed Contrastive Loss for Noisy Label Learning

While collecting training data, even with the manual verification of experts from crowdsourcing platforms, eliminating incorrect annotations (noisy labels) completely is difficult and expensive. In dealing with datasets that contain noisy labels, over-parameterized deep neural networks (DNNs) tend t...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Qian Zhang, Ge Jin, Yi Zhu, Hongjian Wei, Qiu Chen
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2024-07-01
Serier:	Entropy
Fag:	deep neural networks noisy labels pseudo-label relaxed contrastive loss Gaussian mixture model
Online adgang:	https://www.mdpi.com/1099-4300/26/7/589
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!