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

模型名称	Accuracy (mean)	Paper Title	Repository
Peer Loss	57.59	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
ILL	65.84	Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
F-div	57.10	When Optimizing $f$-divergence is Robust with Label Noise
PGDF	74.08	Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
T-Revision	51.55	Are Anchor Points Really Indispensable in Label-Noise Learning?
VolMinNet	57.80	Provably End-to-end Label-Noise Learning without Anchor Points
CE	55.50	-	-
Backward-T	57.14	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
Co-Teaching	60.37	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Positive-LS	55.84	Does label smoothing mitigate label noise?	-
CAL	61.73	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
ELR+	66.72	Early-Learning Regularization Prevents Memorization of Noisy Labels
Divide-Mix	71.13	DivideMix: Learning with Noisy Labels as Semi-supervised Learning
Negative-LS	58.59	To Smooth or Not? When Label Smoothing Meets Noisy Labels
CORES*	55.72	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
ELR	58.94	Early-Learning Regularization Prevents Memorization of Noisy Labels
Forward-T	57.01	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
JoCoR	59.97	Combating noisy labels by agreement: A joint training method with co-regularization
CORES	61.15	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
GCE	56.73	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels

0 of 24 row(s) selected.