Learning With Noisy Labels On Cifar 100N

评估指标

Accuracy (mean)

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
PGDF	74.08	Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
ProMix	73.39	ProMix: Combating Label Noise via Maximizing Clean Sample Utility
PSSCL	72.00	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels	-
Divide-Mix	71.13	DivideMix: Learning with Noisy Labels as Semi-supervised Learning
SOP+	67.81	Robust Training under Label Noise by Over-parameterization
ELR+	66.72	Early-Learning Regularization Prevents Memorization of Noisy Labels
ILL	65.84	Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
CAL	61.73	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
CORES	61.15	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
Co-Teaching	60.37	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
JoCoR	59.97	Combating noisy labels by agreement: A joint training method with co-regularization
ELR	58.94	Early-Learning Regularization Prevents Memorization of Noisy Labels
Negative-LS	58.59	To Smooth or Not? When Label Smoothing Meets Noisy Labels
Co-Teaching+	57.88	How does Disagreement Help Generalization against Label Corruption?
VolMinNet	57.80	Provably End-to-end Label-Noise Learning without Anchor Points
Peer Loss	57.59	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
Backward-T	57.14	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
F-div	57.10	When Optimizing $f$-divergence is Robust with Label Noise
Forward-T	57.01	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
GCE	56.73	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels

0 of 24 row(s) selected.