Document Text Classification on CIFAR-100N

Metric: Accuracy (mean) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy (mean)▼	Extra Data	Paper	Date↕	Code
1	PGDF	74.08	No	Sample Prior Guided Robust Model Learning to Sup...	2021-12-02	Code
2	ProMix	73.39	No	ProMix: Combating Label Noise via Maximizing Cle...	2022-07-21	Code
3	PSSCL	72	No	-	-	Code
4	Divide-Mix	71.13	No	DivideMix: Learning with Noisy Labels as Semi-su...	2020-02-18	Code
5	SOP+	67.81	No	Robust Training under Label Noise by Over-parame...	2022-02-28	Code
6	ELR+	66.72	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
7	ILL	65.84	No	Imprecise Label Learning: A Unified Framework fo...	2023-05-22	Code
8	CAL	61.73	No	Clusterability as an Alternative to Anchor Point...	2021-02-10	Code
9	CORES	61.15	No	Learning with Instance-Dependent Label Noise: A ...	2020-10-05	Code
10	Co-Teaching	60.37	No	Co-teaching: Robust Training of Deep Neural Netw...	2018-04-18	Code
11	JoCoR	59.97	No	Combating noisy labels by agreement: A joint tra...	2020-03-05	Code
12	ELR	58.94	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
13	Negative-LS	58.59	No	To Smooth or Not? When Label Smoothing Meets Noi...	2021-06-08	Code
14	Co-Teaching+	57.88	No	How does Disagreement Help Generalization agains...	2019-01-14	Code
15	VolMinNet	57.8	No	Provably End-to-end Label-Noise Learning without...	2021-02-04	Code
16	Peer Loss	57.59	No	Peer Loss Functions: Learning from Noisy Labels ...	2019-10-08	Code
17	Backward-T	57.14	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code
18	F-div	57.1	No	When Optimizing $f$-divergence is Robust with La...	2020-11-07	Code
19	Forward-T	57.01	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code
20	GCE	56.73	No	Generalized Cross Entropy Loss for Training Deep...	2018-05-20	Code
21	Positive-LS	55.84	No	Does label smoothing mitigate label noise?	2020-03-05	-
22	CORES*	55.72	No	Learning with Instance-Dependent Label Noise: A ...	2020-10-05	Code
23	CE	55.5	No	-	-	-
24	T-Revision	51.55	No	Are Anchor Points Really Indispensable in Label-...	2019-06-01	Code

#1PGDFSOTA
74.08
Accuracy (mean)· 2021-12-02
Sample Prior Guided Robust Model Learning to Suppress Noisy Labels Code
#2ProMix
73.39
Accuracy (mean)· 2022-07-21
ProMix: Combating Label Noise via Maximizing Clean Sample Utility Code
#3PSSCL
72
Accuracy (mean)
No paperCode
#4Divide-MixSOTA
71.13
Accuracy (mean)· 2020-02-18
DivideMix: Learning with Noisy Labels as Semi-supervised Learning Code
#5SOP+
67.81
Accuracy (mean)· 2022-02-28
Robust Training under Label Noise by Over-parameterization Code
#6ELR+
66.72
Accuracy (mean)· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#7ILL
65.84
Accuracy (mean)· 2023-05-22
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations Code
#8CAL
61.73
Accuracy (mean)· 2021-02-10
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels Code
#9CORES
61.15
Accuracy (mean)· 2020-10-05
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach Code
#10Co-TeachingSOTA
60.37
Accuracy (mean)· 2018-04-18
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels Code
#11JoCoR
59.97
Accuracy (mean)· 2020-03-05
Combating noisy labels by agreement: A joint training method with co-regularization Code
#12ELR
58.94
Accuracy (mean)· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#13Negative-LS
58.59
Accuracy (mean)· 2021-06-08
To Smooth or Not? When Label Smoothing Meets Noisy Labels Code
#14Co-Teaching+
57.88
Accuracy (mean)· 2019-01-14
How does Disagreement Help Generalization against Label Corruption?Code
#15VolMinNet
57.8
Accuracy (mean)· 2021-02-04
Provably End-to-end Label-Noise Learning without Anchor Points Code
#16Peer Loss
57.59
Accuracy (mean)· 2019-10-08
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates Code
#17Backward-TSOTA
57.14
Accuracy (mean)· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code
#18F-div
57.1
Accuracy (mean)· 2020-11-07
When Optimizing $f$-divergence is Robust with Label Noise Code
#19Forward-T
57.01
Accuracy (mean)· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code
#20GCE
56.73
Accuracy (mean)· 2018-05-20
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels Code
#21Positive-LS
55.84
Accuracy (mean)· 2020-03-05
Does label smoothing mitigate label noise?
#22CORES*
55.72
Accuracy (mean)· 2020-10-05
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach Code
#23CE
55.5
Accuracy (mean)
No paper
#24T-Revision
51.55
Accuracy (mean)· 2019-06-01
Are Anchor Points Really Indispensable in Label-Noise Learning?Code