Image Classification on CIFAR-10, 4000 Labels

Metric: Percentage error (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Percentage error▲	Extra Data	Paper	Date↕	Code
1	SimMatch	3.96	No	SimMatch: Semi-supervised Learning with Similari...	2022-03-14	Code
2	Self Meta Pseudo Labels	4.09	No	Self Meta Pseudo Labels: Meta Pseudo Labels With...	2022-12-27	-
3	FixMatch+CR	4.16	No	Contrastive Regularization for Semi-Supervised L...	2022-01-17	-
4	EnAET	4.18	No	EnAET: A Self-Trained framework for Semi-Supervi...	2019-11-21	Code
5	UPS (wrn-28-2)	4.25	No	NP-Match: When Neural Processes meet Semi-Superv...	2022-07-03	Code
6	FixMatch (CTA)	4.31	No	FixMatch: Simplifying Semi-Supervised Learning w...	2020-01-21	Code
7	UPS (Shake-Shake)	4.86	No	In Defense of Pseudo-Labeling: An Uncertainty-Aw...	2021-01-15	Code
8	SWSA	5	No	There Are Many Consistent Explanations of Unlabe...	2018-06-14	Code
9	ReMixMatch	5.14	No	ReMixMatch: Semi-Supervised Learning with Distri...	2019-11-21	Code
10	UDA	5.27	No	Unsupervised Data Augmentation for Consistency T...	2019-04-29	Code
11	R2-D2 (Shake-Shake)	5.72	No	Repetitive Reprediction Deep Decipher for Semi-S...	2019-08-09	Code
12	DMT (WRN-28-2)	5.79	No	DMT: Dynamic Mutual Training for Semi-Supervised...	2020-04-18	Code
13	SHOT-VAE	6.11	No	SHOT-VAE: Semi-supervised Deep Generative Models...	2020-11-21	Code
14	MixMatch	6.24	No	MixMatch: A Holistic Approach to Semi-Supervised...	2019-05-06	Code
15	Mean Teacher	6.28	No	Mean teachers are better role models: Weight-ave...	2017-03-06	Code
16	RealMix	6.38	No	RealMix: Towards Realistic Semi-Supervised Deep ...	2019-12-18	Code
17	Triple-GAN-V2 (ResNet-26)	6.54	No	Triple Generative Adversarial Networks	2019-12-20	Code
18	ICT (CNN-13)	7.29	No	Interpolation Consistency Training for Semi-Supe...	2019-03-09	Code
19	LiDAM	7.48	No	LiDAM: Semi-Supervised Learning with Localized D...	2020-10-13	-
20	ICT (WRN-28-2)	7.66	No	Interpolation Consistency Training for Semi-Supe...	2019-03-09	Code
21	ADA-Net (ConvNet)	8.72	No	Semi-Supervised Learning by Augmented Distributi...	2019-05-20	Code
22	Dual Student (600)	8.89	No	Dual Student: Breaking the Limits of the Teacher...	2019-09-03	Code
23	Triple-GAN-V2 (CNN-13)	10.01	No	Triple Generative Adversarial Networks	2019-12-20	Code
24	VAT+EntMin	10.55	No	Virtual Adversarial Training: A Regularization M...	2017-04-13	Code
25	GLOT-DR	10.6	No	Global-Local Regularization Via Distributional R...	2022-03-01	Code
26	VAT	11.36	No	Virtual Adversarial Training: A Regularization M...	2017-04-13	Code
27	SESEMI SSL (ConvNet)	11.65	No	Exploring Self-Supervised Regularization for Sup...	2019-06-25	Code
28	Pi Model	12.16	No	Temporal Ensembling for Semi-Supervised Learning	2016-10-07	Code
29	Triple-GAN-V2 (CNN-13, no aug)	12.41	No	Triple Generative Adversarial Networks	2019-12-20	Code
30	Bad GAN	14.41	No	Good Semi-supervised Learning that Requires a Ba...	2017-05-27	Code
31	GAN	15.59	No	Improved Techniques for Training GANs	2016-06-10	Code
32	Γ-model	20.4	No	Semi-Supervised Learning with Ladder Networks	2015-07-09	Code

#1SimMatchSOTA
3.96
Percentage error· 2022-03-14
SimMatch: Semi-supervised Learning with Similarity Matching Code
#2Self Meta Pseudo Labels
4.09
Percentage error· 2022-12-27
Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher
#3FixMatch+CRSOTA
4.16
Percentage error· 2022-01-17
Contrastive Regularization for Semi-Supervised Learning
#4EnAETSOTA
4.18
Percentage error· 2019-11-21
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations Code
#5UPS (wrn-28-2)
4.25
Percentage error· 2022-07-03
NP-Match: When Neural Processes meet Semi-Supervised Learning Code
#6FixMatch (CTA)
4.31
Percentage error· 2020-01-21
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence Code
#7UPS (Shake-Shake)
4.86
Percentage error· 2021-01-15
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning Code
#8SWSASOTA
5
Percentage error· 2018-06-14
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average Code
#9ReMixMatch
5.14
Percentage error· 2019-11-21
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring Code
#10UDA
5.27
Percentage error· 2019-04-29
Unsupervised Data Augmentation for Consistency Training Code
#11R2-D2 (Shake-Shake)
5.72
Percentage error· 2019-08-09
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning Code
#12DMT (WRN-28-2)
5.79
Percentage error· 2020-04-18
DMT: Dynamic Mutual Training for Semi-Supervised Learning Code
#13SHOT-VAE
6.11
Percentage error· 2020-11-21
SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximations Code
#14MixMatch
6.24
Percentage error· 2019-05-06
MixMatch: A Holistic Approach to Semi-Supervised Learning Code
#15Mean TeacherSOTA
6.28
Percentage error· 2017-03-06
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results Code
#16RealMix
6.38
Percentage error· 2019-12-18
RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms Code
#17Triple-GAN-V2 (ResNet-26)
6.54
Percentage error· 2019-12-20
Triple Generative Adversarial Networks Code
#18ICT (CNN-13)
7.29
Percentage error· 2019-03-09
Interpolation Consistency Training for Semi-Supervised Learning Code
#19LiDAM
7.48
Percentage error· 2020-10-13
LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching
#20ICT (WRN-28-2)
7.66
Percentage error· 2019-03-09
Interpolation Consistency Training for Semi-Supervised Learning Code
#21ADA-Net (ConvNet)
8.72
Percentage error· 2019-05-20
Semi-Supervised Learning by Augmented Distribution Alignment Code
#22Dual Student (600)
8.89
Percentage error· 2019-09-03
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning Code
#23Triple-GAN-V2 (CNN-13)
10.01
Percentage error· 2019-12-20
Triple Generative Adversarial Networks Code
#24VAT+EntMin
10.55
Percentage error· 2017-04-13
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning Code
#25GLOT-DR
10.6
Percentage error· 2022-03-01
Global-Local Regularization Via Distributional Robustness Code
#26VAT
11.36
Percentage error· 2017-04-13
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning Code
#27SESEMI SSL (ConvNet)
11.65
Percentage error· 2019-06-25
Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning Code
#28Pi ModelSOTA
12.16
Percentage error· 2016-10-07
Temporal Ensembling for Semi-Supervised Learning Code
#29Triple-GAN-V2 (CNN-13, no aug)
12.41
Percentage error· 2019-12-20
Triple Generative Adversarial Networks Code
#30Bad GAN
14.41
Percentage error· 2017-05-27
Good Semi-supervised Learning that Requires a Bad GAN Code
#31GANSOTA
15.59
Percentage error· 2016-06-10
Improved Techniques for Training GANs Code
#32Γ-modelSOTA
20.4
Percentage error· 2015-07-09
Semi-Supervised Learning with Ladder Networks Code