Document Text Classification on CIFAR-10N-Aggregate

Metric: Accuracy (mean) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy (mean)▼	Extra Data	Paper	Date↕	Code
1	ProMix	97.39	No	ProMix: Combating Label Noise via Maximizing Cle...	2022-07-21	Code
2	PSSCL	96.41	No	-	-	Code
3	PGDF	96.11	No	Sample Prior Guided Robust Model Learning to Sup...	2021-12-02	Code
4	SOP+	95.61	No	Robust Training under Label Noise by Over-parame...	2022-02-28	Code
5	ILL	95.47	No	Imprecise Label Learning: A Unified Framework fo...	2023-05-22	Code
6	CORES*	95.25	No	Learning with Instance-Dependent Label Noise: A ...	2020-10-05	Code
7	Divide-Mix	95.01	No	DivideMix: Learning with Noisy Labels as Semi-su...	2020-02-18	Code
8	ELR+	94.83	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
9	PES (Semi)	94.66	No	Understanding and Improving Early Stopping for L...	2021-06-30	Code
10	GNL	92.57	No	Partial Label Supervision for Agnostic Generativ...	2023-08-02	Code
11	ELR	92.38	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
12	CAL	91.97	No	Clusterability as an Alternative to Anchor Point...	2021-02-10	Code
13	Negative-LS	91.97	No	To Smooth or Not? When Label Smoothing Meets Noi...	2021-06-08	Code
14	F-div	91.64	No	When Optimizing $f$-divergence is Robust with La...	2020-11-07	Code
15	Positive-LS	91.57	No	Does label smoothing mitigate label noise?	2020-03-05	-
16	JoCoR	91.44	No	Combating noisy labels by agreement: A joint tra...	2020-03-05	Code
17	CORES	91.23	No	Learning with Instance-Dependent Label Noise: A ...	2020-10-05	Code
18	Co-Teaching	91.2	No	Co-teaching: Robust Training of Deep Neural Netw...	2018-04-18	Code
19	Peer Loss	90.75	No	Peer Loss Functions: Learning from Noisy Labels ...	2019-10-08	Code
20	Co-Teaching+	90.61	No	How does Disagreement Help Generalization agains...	2019-01-14	Code
21	VolMinNet	89.7	No	Provably End-to-end Label-Noise Learning without...	2021-02-04	Code
22	T-Revision	88.52	No	Are Anchor Points Really Indispensable in Label-...	2019-06-01	Code
23	Forward-T	88.24	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code
24	Backward-T	88.13	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code
25	GCE	87.85	No	Generalized Cross Entropy Loss for Training Deep...	2018-05-20	Code
26	CE	87.77	No	-	-	-

#1ProMixSOTA
97.39
Accuracy (mean)· 2022-07-21
ProMix: Combating Label Noise via Maximizing Clean Sample Utility Code
#2PSSCL
96.41
Accuracy (mean)
No paperCode
#3PGDFSOTA
96.11
Accuracy (mean)· 2021-12-02
Sample Prior Guided Robust Model Learning to Suppress Noisy Labels Code
#4SOP+
95.61
Accuracy (mean)· 2022-02-28
Robust Training under Label Noise by Over-parameterization Code
#5ILL
95.47
Accuracy (mean)· 2023-05-22
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations Code
#6CORES*SOTA
95.25
Accuracy (mean)· 2020-10-05
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach Code
#7Divide-MixSOTA
95.01
Accuracy (mean)· 2020-02-18
DivideMix: Learning with Noisy Labels as Semi-supervised Learning Code
#8ELR+
94.83
Accuracy (mean)· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#9PES (Semi)
94.66
Accuracy (mean)· 2021-06-30
Understanding and Improving Early Stopping for Learning with Noisy Labels Code
#10GNL
92.57
Accuracy (mean)· 2023-08-02
Partial Label Supervision for Agnostic Generative Noisy Label Learning Code
#11ELR
92.38
Accuracy (mean)· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#12CAL
91.97
Accuracy (mean)· 2021-02-10
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels Code
#13Negative-LS
91.97
Accuracy (mean)· 2021-06-08
To Smooth or Not? When Label Smoothing Meets Noisy Labels Code
#14F-div
91.64
Accuracy (mean)· 2020-11-07
When Optimizing $f$-divergence is Robust with Label Noise Code
#15Positive-LS
91.57
Accuracy (mean)· 2020-03-05
Does label smoothing mitigate label noise?
#16JoCoR
91.44
Accuracy (mean)· 2020-03-05
Combating noisy labels by agreement: A joint training method with co-regularization Code
#17CORES
91.23
Accuracy (mean)· 2020-10-05
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach Code
#18Co-TeachingSOTA
91.2
Accuracy (mean)· 2018-04-18
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels Code
#19Peer Loss
90.75
Accuracy (mean)· 2019-10-08
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates Code
#20Co-Teaching+
90.61
Accuracy (mean)· 2019-01-14
How does Disagreement Help Generalization against Label Corruption?Code
#21VolMinNet
89.7
Accuracy (mean)· 2021-02-04
Provably End-to-end Label-Noise Learning without Anchor Points Code
#22T-Revision
88.52
Accuracy (mean)· 2019-06-01
Are Anchor Points Really Indispensable in Label-Noise Learning?Code
#23Forward-TSOTA
88.24
Accuracy (mean)· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code
#24Backward-T
88.13
Accuracy (mean)· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code
#25GCE
87.85
Accuracy (mean)· 2018-05-20
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels Code
#26CE
87.77
Accuracy (mean)
No paper