Image Classification on mini WebVision 1.0

Metric: Top-5 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Top-5 Accuracy▼	Extra Data	Paper	Date↕	Code
1	PSSCL (130 epochs)	94.84	No	-	-	Code
2	Robust LR	94.12	No	Two Wrongs Don't Make a Right: Combating Confirm...	2021-12-06	-
3	PGDF (Inception-ResNet-v2)	94.03	No	Sample Prior Guided Robust Model Learning to Sup...	2021-12-02	Code
4	PSSCL (120 epochs)	93.8	No	-	-	Code
5	Dynamic Loss (Inception-ResNet-v2)	93.64	No	Dynamic Loss For Robust Learning	2022-11-22	Code
6	CC	93.64	No	Centrality and Consistency: Two-Stage Clean Samp...	2022-07-29	Code
7	CoDiM-Self (Inception-ResNet-v2)	93.52	No	CoDiM: Learning with Noisy Labels via Contrastiv...	2021-11-23	-
8	CMW-Net-SL+C2D	93.36	No	CMW-Net: Learning a Class-Aware Sample Weighting...	2022-02-11	Code
9	CMW-Net-SL	92.96	No	CMW-Net: Learning a Class-Aware Sample Weighting...	2022-02-11	Code
10	SSR	92.8	No	SSR: An Efficient and Robust Framework for Learn...	2021-11-22	Code
11	FaMUS	92.8	No	Faster Meta Update Strategy for Noise-Robust Dee...	2021-04-30	Code
12	BtR	92.76	No	Bootstrapping the Relationship Between Images an...	2022-10-17	Code
13	Sel-CL+ (ResNet-18)	92.64	No	Selective-Supervised Contrastive Learning with N...	2022-03-08	Code
14	CoDiM-Sup (Inception-ResNet-v2)	92.48	No	CoDiM: Learning with Noisy Labels via Contrastiv...	2021-11-23	-
15	ROLT+ (Inception-ResNet-v2)	92.44	No	Robust Long-Tailed Learning under Label Noise	2021-08-26	-
16	LongReMix (Inception-ResNet-v2)	92.32	No	LongReMix: Robust Learning with High Confidence ...	2021-03-06	Code
17	TCL	92.3	No	Twin Contrastive Learning with Noisy Labels	2023-03-13	Code
18	CAR	92.25	No	Confidence Adaptive Regularization for Deep Lear...	2021-08-18	-
19	NGC (Inception-ResNet-v2)	91.84	No	NGC: A Unified Framework for Learning with Open-...	2021-08-25	-
20	ELR+ (Inception-ResNet-v2)	91.68	No	Early-Learning Regularization Prevents Memorizat...	2020-06-30	Code
21	DivideMix (Inception-ResNet-v2)	91.64	No	DivideMix: Learning with Noisy Labels as Semi-su...	2020-02-18	Code
22	GJS (ResNet-50)	91.22	No	Generalized Jensen-Shannon Divergence Loss for L...	2021-05-10	Code
23	NCT (Inception-ResNet-v2)	90.77	No	Noisy Concurrent Training for Efficient Learning...	2020-09-17	Code
24	ODD (Inception-ResNet-v2)	90.6	No	Robust and On-the-fly Dataset Denoising for Imag...	2020-03-24	-
25	MentorMix (Inception-ResNet-v2)	90.2	No	Beyond Synthetic Noise: Deep Learning on Control...	2019-11-21	Code
26	Crust (Inception-ResNet-v2)	89.56	No	Coresets for Robust Training of Neural Networks ...	2020-11-15	-
27	Iterative-CV (Inception-ResNet-v2)	85.3	No	Understanding and Utilizing Deep Neural Networks...	2019-05-13	Code
28	Co-teaching (Inception-ResNet-v2)	85.2	No	Co-teaching: Robust Training of Deep Neural Netw...	2018-04-18	Code
29	D2L (Inception-ResNet-v2)	84	No	Dimensionality-Driven Learning with Noisy Labels	2018-06-07	Code
30	F-Correction (Inception-ResNet-v2)	82.68	No	Making Deep Neural Networks Robust to Label Nois...	2016-09-13	Code

#1PSSCL (130 epochs)
94.84
Top-5 Accuracy
No paperCode
#2Robust LRSOTA
94.12
Top-5 Accuracy· 2021-12-06
Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise
#3PGDF (Inception-ResNet-v2)SOTA
94.03
Top-5 Accuracy· 2021-12-02
Sample Prior Guided Robust Model Learning to Suppress Noisy Labels Code
#4PSSCL (120 epochs)
93.8
Top-5 Accuracy
No paperCode
#5Dynamic Loss (Inception-ResNet-v2)
93.64
Top-5 Accuracy· 2022-11-22
Dynamic Loss For Robust Learning Code
#6CC
93.64
Top-5 Accuracy· 2022-07-29
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels Code
#7CoDiM-Self (Inception-ResNet-v2)SOTA
93.52
Top-5 Accuracy· 2021-11-23
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
#8CMW-Net-SL+C2D
93.36
Top-5 Accuracy· 2022-02-11
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning Code
#9CMW-Net-SL
92.96
Top-5 Accuracy· 2022-02-11
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning Code
#10SSR
92.8
Top-5 Accuracy· 2021-11-22
SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise Code
#11FaMUSSOTA
92.8
Top-5 Accuracy· 2021-04-30
Faster Meta Update Strategy for Noise-Robust Deep Learning Code
#12BtR
92.76
Top-5 Accuracy· 2022-10-17
Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels Code
#13Sel-CL+ (ResNet-18)
92.64
Top-5 Accuracy· 2022-03-08
Selective-Supervised Contrastive Learning with Noisy Labels Code
#14CoDiM-Sup (Inception-ResNet-v2)
92.48
Top-5 Accuracy· 2021-11-23
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
#15ROLT+ (Inception-ResNet-v2)
92.44
Top-5 Accuracy· 2021-08-26
Robust Long-Tailed Learning under Label Noise
#16LongReMix (Inception-ResNet-v2)SOTA
92.32
Top-5 Accuracy· 2021-03-06
LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment Code
#17TCL
92.3
Top-5 Accuracy· 2023-03-13
Twin Contrastive Learning with Noisy Labels Code
#18CAR
92.25
Top-5 Accuracy· 2021-08-18
Confidence Adaptive Regularization for Deep Learning with Noisy Labels
#19NGC (Inception-ResNet-v2)
91.84
Top-5 Accuracy· 2021-08-25
NGC: A Unified Framework for Learning with Open-World Noisy Data
#20ELR+ (Inception-ResNet-v2)SOTA
91.68
Top-5 Accuracy· 2020-06-30
Early-Learning Regularization Prevents Memorization of Noisy Labels Code
#21DivideMix (Inception-ResNet-v2)SOTA
91.64
Top-5 Accuracy· 2020-02-18
DivideMix: Learning with Noisy Labels as Semi-supervised Learning Code
#22GJS (ResNet-50)
91.22
Top-5 Accuracy· 2021-05-10
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels Code
#23NCT (Inception-ResNet-v2)
90.77
Top-5 Accuracy· 2020-09-17
Noisy Concurrent Training for Efficient Learning under Label Noise Code
#24ODD (Inception-ResNet-v2)
90.6
Top-5 Accuracy· 2020-03-24
Robust and On-the-fly Dataset Denoising for Image Classification
#25MentorMix (Inception-ResNet-v2)SOTA
90.2
Top-5 Accuracy· 2019-11-21
Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels Code
#26Crust (Inception-ResNet-v2)
89.56
Top-5 Accuracy· 2020-11-15
Coresets for Robust Training of Neural Networks against Noisy Labels
#27Iterative-CV (Inception-ResNet-v2)SOTA
85.3
Top-5 Accuracy· 2019-05-13
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels Code
#28Co-teaching (Inception-ResNet-v2)SOTA
85.2
Top-5 Accuracy· 2018-04-18
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels Code
#29D2L (Inception-ResNet-v2)
84
Top-5 Accuracy· 2018-06-07
Dimensionality-Driven Learning with Noisy Labels Code
#30F-Correction (Inception-ResNet-v2)SOTA
82.68
Top-5 Accuracy· 2016-09-13
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach Code