Image Classification on CIFAR-10N-Random2

Metric: Accuracy (mean) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Accuracy (mean)▼	Extra Data	Paper	Date↕	Code
1	PSSCL	96.21	No	-	-	Code
2	SOP	95.31	No	Robust Training under Label Noise by Over-parame...	2022-02-28	Code
3	ILL	95.04	No	Imprecise Label Learning: A Unified Framework fo...	2023-05-22	Code
4	CORES*	94.88	No	Learning with Instance-Dependent Label Noise: A ...	2020-10-05	Code
5	ELR+	94.2	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
6	ELR	91.61	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
7	GNL	91.42	No	Partial Label Supervision for Agnostic Generativ...	2023-08-02	Code
8	Divide-Mix	90.9	No	DivideMix: Learning with Noisy Labels as Semi-su...	2020-02-18	Code
9	CAL	90.75	No	Clusterability as an Alternative to Anchor Point...	2021-02-10	Code
10	Negative-LS	90.37	No	To Smooth or Not? When Label Smoothing Meets Noi...	2021-06-08	Code
11	Co-Teaching	90.3	No	Co-teaching: Robust Training of Deep Neural Netw...	2018-04-18	Code
12	JoCoR	90.21	No	Combating noisy labels by agreement: A joint tra...	2020-03-05	Code
13	CORES	89.91	No	Learning with Instance-Dependent Label Noise: A ...	2020-10-05	Code
14	F-div	89.79	No	When Optimizing $f$-divergence is Robust with La...	2020-11-07	Code
15	Co-Teaching+	89.47	No	How does Disagreement Help Generalization agains...	2019-01-14	Code
16	Positive-LS	89.35	No	Does label smoothing mitigate label noise?	2020-03-05	-
17	Peer Loss	88.76	No	Peer Loss Functions: Learning from Noisy Labels ...	2019-10-08	Code
18	VolMinNet	88.27	No	Provably End-to-end Label-Noise Learning without...	2021-02-04	Code
19	T-Revision	87.71	No	Are Anchor Points Really Indispensable in Label-...	2019-06-01	Code
20	GCE	87.7	No	Generalized Cross Entropy Loss for Training Deep...	2018-05-20	Code
21	CE	86.46	No	-	-	-
22	Backward-T	86.28	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code
23	Forward-T	86.14	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code

#1PSSCL
96.21
Accuracy (mean)
No paperCode
#2SOPSOTA
95.31
Accuracy (mean)· 2022-02-28
Robust Training under Label Noise by Over-parameterization Code
#3ILL
95.04
Accuracy (mean)· 2023-05-22
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations Code
#4CORES*SOTA
94.88
Accuracy (mean)· 2020-10-05
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach Code
#5ELR+SOTA
94.2
Accuracy (mean)· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#6ELR
91.61
Accuracy (mean)· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#7GNL
91.42
Accuracy (mean)· 2023-08-02
Partial Label Supervision for Agnostic Generative Noisy Label Learning Code
#8Divide-MixSOTA
90.9
Accuracy (mean)· 2020-02-18
DivideMix: Learning with Noisy Labels as Semi-supervised Learning Code
#9CAL
90.75
Accuracy (mean)· 2021-02-10
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels Code
#10Negative-LS
90.37
Accuracy (mean)· 2021-06-08
To Smooth or Not? When Label Smoothing Meets Noisy Labels Code
#11Co-TeachingSOTA
90.3
Accuracy (mean)· 2018-04-18
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels Code
#12JoCoR
90.21
Accuracy (mean)· 2020-03-05
Combating noisy labels by agreement: A joint training method with co-regularization Code
#13CORES
89.91
Accuracy (mean)· 2020-10-05
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach Code
#14F-div
89.79
Accuracy (mean)· 2020-11-07
When Optimizing $f$-divergence is Robust with Label Noise Code
#15Co-Teaching+
89.47
Accuracy (mean)· 2019-01-14
How does Disagreement Help Generalization against Label Corruption?Code
#16Positive-LS
89.35
Accuracy (mean)· 2020-03-05
Does label smoothing mitigate label noise?
#17Peer Loss
88.76
Accuracy (mean)· 2019-10-08
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates Code
#18VolMinNet
88.27
Accuracy (mean)· 2021-02-04
Provably End-to-end Label-Noise Learning without Anchor Points Code
#19T-Revision
87.71
Accuracy (mean)· 2019-06-01
Are Anchor Points Really Indispensable in Label-Noise Learning?Code
#20GCE
87.7
Accuracy (mean)· 2018-05-20
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels Code
#21CE
86.46
Accuracy (mean)
No paper
#22Backward-TSOTA
86.28
Accuracy (mean)· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code
#23Forward-T
86.14
Accuracy (mean)· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code