Learning With Noisy Labels On Cifar 10N 1

Metrics

Accuracy (mean)

Results

Performance results of various models on this benchmark

		Paper Title
ProMix	96.97	ProMix: Combating Label Noise via Maximizing Clean Sample Utility
PSSCL	96.17	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels
PGDF	96.01	Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
SOP+	95.28	Robust Training under Label Noise by Over-parameterization
ILL	94.85	Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
CORES*	94.45	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
ELR+	94.43	Early-Learning Regularization Prevents Memorization of Noisy Labels
GNL	91.97	Partial Label Supervision for Agnostic Generative Noisy Label Learning
ELR	91.46	Early-Learning Regularization Prevents Memorization of Noisy Labels
CAL	90.93	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Co-Teaching	90.33	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
JoCoR	90.30	Combating noisy labels by agreement: A joint training method with co-regularization
Negative-LS	90.29	To Smooth or Not? When Label Smoothing Meets Noisy Labels
Divide-Mix	90.18	DivideMix: Learning with Noisy Labels as Semi-supervised Learning
Positive-LS	89.80	Does label smoothing mitigate label noise?
F-div	89.70	When Optimizing $f$-divergence is Robust with Label Noise
Co-Teaching+	89.70	How does Disagreement Help Generalization against Label Corruption?
CORES	89.66	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
Peer Loss	89.06	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
T-Revision	88.33	Are Anchor Points Really Indispensable in Label-Noise Learning?

0 of 24 row(s) selected.

Command Palette

Learning With Noisy Labels On Cifar 10N 1

Metrics

Results

Command Palette

Learning With Noisy Labels On Cifar 10N 1

Metrics

Results