Learning With Noisy Labels On Cifar 10N Worst

Métriques

Accuracy (mean)

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy (mean)	Paper Title	Repository
Co-Teaching	83.83	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels	-
ELR	83.58	Early-Learning Regularization Prevents Memorization of Noisy Labels	-
GNL	86.99	Partial Label Supervision for Agnostic Generative Noisy Label Learning	-
T-Revision	80.48	Are Anchor Points Really Indispensable in Label-Noise Learning?	-
JoCoR	83.37	Combating noisy labels by agreement: A joint training method with co-regularization	-
PSSCL	95.12	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels
PGDF	93.65	Sample Prior Guided Robust Model Learning to Suppress Noisy Labels	-
CE	77.69	-	-
Negative-LS	82.99	Understanding Generalized Label Smoothing when Learning with Noisy Labels	-
Forward-T	79.79	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach	-
Co-Teaching+	83.26	How does Disagreement Help Generalization against Label Corruption?	-
F-div	82.53	When Optimizing $f$-divergence is Robust with Label Noise	-
ProMix	96.16	ProMix: Combating Label Noise via Maximizing Clean Sample Utility	-
GCE	80.66	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels	-
Divide-Mix	92.56	DivideMix: Learning with Noisy Labels as Semi-supervised Learning	-
CAL	85.36	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels	-
VolMinNet	80.53	Provably End-to-end Label-Noise Learning without Anchor Points	-
CORES	83.60	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach	-
ELR+	91.09	Early-Learning Regularization Prevents Memorization of Noisy Labels	-
Peer Loss	82.53	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates	-

0 of 25 row(s) selected.