Few-Shot Image Classification on CIFAR-100-LT (ρ=100)

Metric: Error Rate (lower is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Error Rate▲	Extra Data	Paper	Date↕	Code
1	LPT	10.9	Yes	LPT: Long-tailed Prompt Tuning for Image Classif...	2022-10-03	Code
2	LIFT (ViT-B/16, ImageNet-21K pre-training)	10.9	Yes	Long-Tail Learning with Foundation Model: Heavy ...	2023-09-18	Code
3	LIFT (ViT-B/16, CLIP)	18.3	Yes	Long-Tail Learning with Foundation Model: Heavy ...	2023-09-18	Code
4	VPT	19	Yes	Visual Prompt Tuning	2022-03-23	Code
5	BALLAD (ViT-B/16)	22.2	Yes	A Simple Long-Tailed Recognition Baseline via Vi...	2021-11-29	Code
6	GLMC + SAM	40.99	No	Escaping Saddle Points for Effective Generalizat...	2022-12-28	Code
7	GLMC+MaxNorm (ResNet-34, channel x4)	41.59	No	Global and Local Mixture Consistency Cumulative ...	2023-05-15	Code
8	GLMC (ResNet-34, channel x4)	42.01	No	Global and Local Mixture Consistency Cumulative ...	2023-05-15	Code
9	SURE(ResNet-32)	43.66	No	SURE: SUrvey REcipes for building reliable and r...	2024-03-01	Code
10	MDCS	43.9	No	MDCS: More Diverse Experts with Consistency Self...	2023-08-19	Code
11	DeiT-LT	44.4	No	DeiT-LT Distillation Strikes Back for Vision Tra...	2024-04-03	Code
12	NCL* + WGCC (ensemble)	44.9	No	-	-	-
13	OPeN (WideResNet-28-10)	45.8	No	Pure Noise to the Rescue of Insufficient Data: I...	2021-12-16	Code
14	GML (ResNet-32)	46	No	Long-Tailed Recognition by Mutual Information Ma...	2023-05-02	Code
15	BCL(ResNet-32)	46.1	No	Balanced Contrastive Learning for Long-Tailed Vi...	2022-07-19	Code
16	LTR-weight-balancing	46.45	No	Long-Tailed Recognition via Weight Balancing	2022-03-27	Code
17	PC	46.59	No	Learning Prototype Classifiers for Long-Tailed R...	2023-02-01	Code
18	NCL(ResNet32)	46.7	No	Nested Collaborative Learning for Long-Tailed Vi...	2022-03-29	Code
19	ConCutMix	46.84	No	Enhanced Long-Tailed Recognition with Contrastiv...	2024-07-06	Code
20	VS + ADRW + TLA	46.95	No	A Unified Generalization Analysis of Re-Weightin...	2023-10-07	Code
21	PaCo + SAM	47	No	Escaping Saddle Points for Effective Generalizat...	2022-12-28	Code
22	Difficulty-Net	47.04	No	Difficulty-Net: Learning to Predict Difficulty f...	2022-09-07	Code
23	Paco + BatchFormer	47.6	No	BatchFormer: Learning to Explore Sample Relation...	2022-03-03	Code
24	GLAG	48.3	No	Long-Tailed Classification with Gradual Balanced...	2022-02-28	-
25	Balanced + BatchFormer	48.3	No	BatchFormer: Learning to Explore Sample Relation...	2022-03-03	Code
26	PCL	49.1	No	Parametric Contrastive Learning	2021-07-26	Code
27	RIDE + CMO + Curvature Regularization	49.3	No	Predicting and Enhancing the Fairness of DNNs wi...	2023-03-22	Code
28	RIDE 3 experts + CMO	50	No	The Majority Can Help The Minority: Context-rich...	2021-12-01	Code
29	TADE	50.2	No	Self-Supervised Aggregation of Diverse Experts f...	2021-07-20	Code
30	TLC (4 Experts)	50.2	No	Trustworthy Long-Tailed Classification	2021-11-17	Code
31	ACE (4 experts)	50.4	No	ACE: Ally Complementary Experts for Solving Long...	2021-08-05	-
32	RIDE+distill	50.9	No	Long-tailed Recognition by Routing Diverse Distr...	2020-10-05	Code
33	GCL	51.29	No	Long-tailed Visual Recognition via Gaussian Clou...	2023-05-19	Code
34	DirMixE	51.62	No	Harnessing Hierarchical Label Distribution Varia...	2024-05-13	Code
35	MetaSAug-LDAM	51.99	No	MetaSAug: Meta Semantic Augmentation for Long-Ta...	2021-03-23	Code
36	RIDE	52	No	Long-tailed Recognition by Routing Diverse Distr...	2020-10-05	Code
37	DRO-LT	52.67	No	Distributional Robustness Loss for Long-tail Lea...	2021-04-07	-
38	LDAM-DRW + CMO	52.8	No	The Majority Can Help The Minority: Context-rich...	2021-12-01	Code
39	MiSLAS	53	No	Improving Calibration for Long-Tailed Recognition	2021-04-01	Code
40	Balanced Softmax + CMO	53.4	No	The Majority Can Help The Minority: Context-rich...	2021-12-01	Code
41	VS + SAM	53.4	No	Escaping Saddle Points for Effective Generalizat...	2022-12-28	Code
42	CBD+TailCalibX	53.41	No	Feature Generation for Long-tail Classification	2021-11-10	Code
43	Prior-LT	53.59	No	Towards Calibrated Model for Long-Tailed Visual ...	2021-11-06	Code
44	OTLM+CE (Resnet-32)	53.9	No	-	-	-
45	SSD	54	No	Self Supervision to Distillation for Long-Tailed...	2021-09-09	Code
46	MBJ	54.2	No	Memory-based Jitter: Improving Visual Recognitio...	2020-08-22	-
47	UniMix+Bayias (ResNet-32)	54.55	No	Towards Calibrated Model for Long-Tailed Visual ...	2021-11-06	Code
48	LADE	54.6	No	Disentangling Label Distribution for Long-tailed...	2020-12-01	Code
49	ETF Classifier + DR (Resnet)	54.7	No	Inducing Neural Collapse in Imbalanced Learning:...	2022-03-17	Code
50	FBL (Resnet-32)	54.78	No	Feature-Balanced Loss for Long-Tailed Visual Rec...	2023-05-18	Code
51	Hybrid-PSC	55.03	No	Contrastive Learning based Hybrid Networks for L...	2021-03-26	-
52	LDAM-DRW-RSG	55.5	No	RSG: A Simple but Effective Module for Learning ...	2021-06-18	Code
53	CE+DRS+GIT	55.65	No	Do Deep Networks Transfer Invariances Across Cla...	2022-03-18	Code
54	TSC(ResNet-32)	56.2	No	Targeted Supervised Contrastive Learning for Lon...	2021-11-27	Code
55	LDAM-DRW + WGCC	56.4	No	-	-	-
56	smDRAGON	56.5	No	From Generalized zero-shot learning to long-tail...	2020-04-05	Code
57	LDAM-DRW + SSP	56.57	No	Rethinking the Value of Labels for Improving Cla...	2020-06-13	Code
58	CE-DRW-IC	56.9	No	Posterior Re-calibration for Imbalanced Datasets	2020-10-22	-
59	CDB-loss	57.43	No	Class-Wise Difficulty-Balanced Loss for Solving ...	2020-10-05	Code
60	ELP	57.6	No	-	-	Code
61	LDAM-DRW	57.96	No	Learning Imbalanced Datasets with Label-Distribu...	2019-06-18	Code
62	CE-DRW	58.9	No	The Majority Can Help The Minority: Context-rich...	2021-12-01	Code
63	Cross-Entropy + Curvature Regularization	59.5	No	Predicting and Enhancing the Fairness of DNNs wi...	2023-03-22	Code
64	IBLLoss	61.52	No	Influence-Balanced Loss for Imbalanced Visual Cl...	2021-10-06	Code
65	Cross-Entropy (CE)	61.68	No	Class-Balanced Loss Based on Effective Number of...	2019-01-16	Code
66	Cross-Entropy (CE)	62.75	No	Revisiting Long-tailed Image Classification: Sur...	2023-02-03	-

#1LPTSOTA
10.9
Error Rate· Extra Data· 2022-10-03
LPT: Long-tailed Prompt Tuning for Image Classification Code
#2LIFT (ViT-B/16, ImageNet-21K pre-training)
10.9
Error Rate· Extra Data· 2023-09-18
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts Code
#3LIFT (ViT-B/16, CLIP)
18.3
Error Rate· Extra Data· 2023-09-18
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts Code
#4VPTSOTA
19
Error Rate· Extra Data· 2022-03-23
Visual Prompt Tuning Code
#5BALLAD (ViT-B/16)SOTA
22.2
Error Rate· Extra Data· 2021-11-29
A Simple Long-Tailed Recognition Baseline via Vision-Language Model Code
#6GLMC + SAM
40.99
Error Rate· 2022-12-28
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data Code
#7GLMC+MaxNorm (ResNet-34, channel x4)
41.59
Error Rate· 2023-05-15
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions Code
#8GLMC (ResNet-34, channel x4)
42.01
Error Rate· 2023-05-15
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions Code
#9SURE(ResNet-32)
43.66
Error Rate· 2024-03-01
SURE: SUrvey REcipes for building reliable and robust deep networks Code
#10MDCS
43.9
Error Rate· 2023-08-19
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition Code
#11DeiT-LT
44.4
Error Rate· 2024-04-03
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets Code
#12NCL* + WGCC (ensemble)
44.9
Error Rate
No paper
#13OPeN (WideResNet-28-10)
45.8
Error Rate· 2021-12-16
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images Code
#14GML (ResNet-32)
46
Error Rate· 2023-05-02
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels Code
#15BCL(ResNet-32)
46.1
Error Rate· 2022-07-19
Balanced Contrastive Learning for Long-Tailed Visual Recognition Code
#16LTR-weight-balancing
46.45
Error Rate· 2022-03-27
Long-Tailed Recognition via Weight Balancing Code
#17PC
46.59
Error Rate· 2023-02-01
Learning Prototype Classifiers for Long-Tailed Recognition Code
#18NCL(ResNet32)
46.7
Error Rate· 2022-03-29
Nested Collaborative Learning for Long-Tailed Visual Recognition Code
#19ConCutMix
46.84
Error Rate· 2024-07-06
Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation Code
#20VS + ADRW + TLA
46.95
Error Rate· 2023-10-07
A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning Code
#21PaCo + SAM
47
Error Rate· 2022-12-28
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data Code
#22Difficulty-Net
47.04
Error Rate· 2022-09-07
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition Code
#23Paco + BatchFormer
47.6
Error Rate· 2022-03-03
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning Code
#24GLAG
48.3
Error Rate· 2022-02-28
Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation
#25Balanced + BatchFormer
48.3
Error Rate· 2022-03-03
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning Code
#26PCLSOTA
49.1
Error Rate· 2021-07-26
Parametric Contrastive Learning Code
#27RIDE + CMO + Curvature Regularization
49.3
Error Rate· 2023-03-22
Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds Code
#28RIDE 3 experts + CMO
50
Error Rate· 2021-12-01
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification Code
#29TADESOTA
50.2
Error Rate· 2021-07-20
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition Code
#30TLC (4 Experts)
50.2
Error Rate· 2021-11-17
Trustworthy Long-Tailed Classification Code
#31ACE (4 experts)
50.4
Error Rate· 2021-08-05
ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot
#32RIDE+distillSOTA
50.9
Error Rate· 2020-10-05
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts Code
#33GCL
51.29
Error Rate· 2023-05-19
Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment Code
#34DirMixE
51.62
Error Rate· 2024-05-13
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition Code
#35MetaSAug-LDAM
51.99
Error Rate· 2021-03-23
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition Code
#36RIDESOTA
52
Error Rate· 2020-10-05
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts Code
#37DRO-LT
52.67
Error Rate· 2021-04-07
Distributional Robustness Loss for Long-tail Learning
#38LDAM-DRW + CMO
52.8
Error Rate· 2021-12-01
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification Code
#39MiSLAS
53
Error Rate· 2021-04-01
Improving Calibration for Long-Tailed Recognition Code
#40Balanced Softmax + CMO
53.4
Error Rate· 2021-12-01
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification Code
#41VS + SAM
53.4
Error Rate· 2022-12-28
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data Code
#42CBD+TailCalibX
53.41
Error Rate· 2021-11-10
Feature Generation for Long-tail Classification Code
#43Prior-LT
53.59
Error Rate· 2021-11-06
Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective Code
#44OTLM+CE (Resnet-32)
53.9
Error Rate
No paper
#45SSD
54
Error Rate· 2021-09-09
Self Supervision to Distillation for Long-Tailed Visual Recognition Code
#46MBJSOTA
54.2
Error Rate· 2020-08-22
Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
#47UniMix+Bayias (ResNet-32)
54.55
Error Rate· 2021-11-06
Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective Code
#48LADE
54.6
Error Rate· 2020-12-01
Disentangling Label Distribution for Long-tailed Visual Recognition Code
#49ETF Classifier + DR (Resnet)
54.7
Error Rate· 2022-03-17
Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?Code
#50FBL (Resnet-32)
54.78
Error Rate· 2023-05-18
Feature-Balanced Loss for Long-Tailed Visual Recognition Code
#51Hybrid-PSC
55.03
Error Rate· 2021-03-26
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
#52LDAM-DRW-RSG
55.5
Error Rate· 2021-06-18
RSG: A Simple but Effective Module for Learning Imbalanced Datasets Code
#53CE+DRS+GIT
55.65
Error Rate· 2022-03-18
Do Deep Networks Transfer Invariances Across Classes?Code
#54TSC(ResNet-32)
56.2
Error Rate· 2021-11-27
Targeted Supervised Contrastive Learning for Long-Tailed Recognition Code
#55LDAM-DRW + WGCC
56.4
Error Rate
No paper
#56smDRAGONSOTA
56.5
Error Rate· 2020-04-05
From Generalized zero-shot learning to long-tail with class descriptors Code
#57LDAM-DRW + SSP
56.57
Error Rate· 2020-06-13
Rethinking the Value of Labels for Improving Class-Imbalanced Learning Code
#58CE-DRW-IC
56.9
Error Rate· 2020-10-22
Posterior Re-calibration for Imbalanced Datasets
#59CDB-loss
57.43
Error Rate· 2020-10-05
Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance Code
#60ELP
57.6
Error Rate
No paperCode
#61LDAM-DRWSOTA
57.96
Error Rate· 2019-06-18
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss Code
#62CE-DRW
58.9
Error Rate· 2021-12-01
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification Code
#63Cross-Entropy + Curvature Regularization
59.5
Error Rate· 2023-03-22
Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds Code
#64IBLLoss
61.52
Error Rate· 2021-10-06
Influence-Balanced Loss for Imbalanced Visual Classification Code
#65Cross-Entropy (CE)SOTA
61.68
Error Rate· 2019-01-16
Class-Balanced Loss Based on Effective Number of Samples Code
#66Cross-Entropy (CE)
62.75
Error Rate· 2023-02-03
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics