Learning With Noisy Labels On Cifar 10N 3

Metriken

Accuracy (mean)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Accuracy (mean)	Paper Title	Repository
GCE	87.58	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
F-div	89.55	When Optimizing $f$-divergence is Robust with Label Noise
CAL	90.74	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Backward-T	86.86	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
CORES	89.79	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
JoCoR	90.11	Combating noisy labels by agreement: A joint training method with co-regularization
Positive-LS	89.82	Does label smoothing mitigate label noise?	-
ELR	91.41	Early-Learning Regularization Prevents Memorization of Noisy Labels
VolMinNet	88.19	Provably End-to-end Label-Noise Learning without Anchor Points
SOP+	95.39	Robust Training under Label Noise by Over-parameterization
Co-Teaching	90.15	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Co-Teaching+	89.54	How does Disagreement Help Generalization against Label Corruption?
Forward-T	87.04	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
PSSCL	96.49	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels
GNL	91.83	Partial Label Supervision for Agnostic Generative Noisy Label Learning
CORES*	94.74	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
ILL	95.13	Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
CE	85.16	-	-
Negative-LS	90.13	To Smooth or Not? When Label Smoothing Meets Noisy Labels
Peer Loss	88.57	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates

0 of 23 row(s) selected.