Learning With Noisy Labels On Cifar 10N 2

Metriken

Accuracy (mean)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy (mean)	Paper Title	Repository
GNL	91.42	Partial Label Supervision for Agnostic Generative Noisy Label Learning
Co-Teaching	90.30	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Peer Loss	88.76	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
GCE	87.70	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
CORES*	94.88	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
ELR+	94.20	Early-Learning Regularization Prevents Memorization of Noisy Labels
Backward-T	86.28	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
T-Revision	87.71	Are Anchor Points Really Indispensable in Label-Noise Learning?
JoCoR	90.21	Combating noisy labels by agreement: A joint training method with co-regularization
SOP	95.31	Robust Training under Label Noise by Over-parameterization
CORES	89.91	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
Forward-T	86.14	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
ELR	91.61	Early-Learning Regularization Prevents Memorization of Noisy Labels
PSSCL	96.21	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels
Divide-Mix	90.90	DivideMix: Learning with Noisy Labels as Semi-supervised Learning
CE	86.46	-	-
CAL	90.75	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Positive-LS	89.35	Does label smoothing mitigate label noise?	-
Negative-LS	90.37	To Smooth or Not? When Label Smoothing Meets Noisy Labels
ILL	95.04	Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations

0 of 23 row(s) selected.