Generalized Few-Shot Classification on CIFAR-100-LT (ρ=50)

Metric: Error Rate (lower is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	Error Rate▲	Augmentations	Paper	Date↕	Code
1	LIFT (ViT-B/16, ImageNet-21K pre-training)	9.8	No	Long-Tail Learning with Foundation Model: Heavy ...	2023-09-18	Code
2	LPT	10	Yes	LPT: Long-tailed Prompt Tuning for Image Classif...	2022-10-03	Code
3	VPT	15.2	Yes	Visual Prompt Tuning	2022-03-23	Code
4	LIFT (ViT-B/16, CLIP)	16.9	No	Long-Tail Learning with Foundation Model: Heavy ...	2023-09-18	Code
5	GLMC + SAM	34.72	No	Escaping Saddle Points for Effective Generalizat...	2022-12-28	Code
6	GLMC (ResNet-34, channel x4)	36.15	No	Global and Local Mixture Consistency Cumulative ...	2023-05-15	Code
7	SURE(ResNet-32)	36.87	No	SURE: SUrvey REcipes for building reliable and r...	2024-03-01	Code
8	DeiT-LT	39.5	No	DeiT-LT Distillation Strikes Back for Vision Tra...	2024-04-03	Code
9	MDCS	39.9	No	MDCS: More Diverse Experts with Consistency Self...	2023-08-19	Code
10	OPeN (WideResNet-28-10)	40.2	No	Pure Noise to the Rescue of Insufficient Data: I...	2021-12-16	Code
11	GML (ResNet-32)	41.9	No	Long-Tailed Recognition by Mutual Information Ma...	2023-05-02	Code
12	PC	42.25	No	Learning Prototype Classifiers for Long-Tailed R...	2023-02-01	Code
13	LTR-weight-balancing	42.29	No	Long-Tailed Recognition via Weight Balancing	2022-03-27	Code
14	ConCutMix	42.6	No	Enhanced Long-Tailed Recognition with Contrastiv...	2024-07-06	Code
15	Difficulty-Net	43.1	No	Difficulty-Net: Learning to Predict Difficulty f...	2022-09-07	Code
16	NCL(ResNet32)	43.2	No	Nested Collaborative Learning for Long-Tailed Vi...	2022-03-29	Code
17	BCL(ResNet-32)	43.4	No	Balanced Contrastive Learning for Long-Tailed Vi...	2022-07-19	Code
18	TADE	46.1	No	Self-Supervised Aggregation of Diverse Experts f...	2021-07-20	Code
19	GCL	46.4	No	Long-tailed Visual Recognition via Gaussian Clou...	2023-05-19	Code
20	MiSLAS	47.7	No	Improving Calibration for Long-Tailed Recognition	2021-04-01	Code
21	MetaSAug-LDAM	47.73	No	MetaSAug: Meta Semantic Augmentation for Long-Ta...	2021-03-23	Code
22	CBD+TailCalibX	49.1	No	Feature Generation for Long-tail Classification	2021-11-10	Code
23	Hybrid-PSC	51.07	No	Contrastive Learning based Hybrid Networks for L...	2021-03-26	-
24	LDAM-DRW-RSG	51.5	No	RSG: A Simple but Effective Module for Learning ...	2021-06-18	Code
25	LDAM-DRW + SSP	52.89	No	Rethinking the Value of Labels for Improving Cla...	2020-06-13	Code

#1LIFT (ViT-B/16, ImageNet-21K pre-training)SOTA
9.8
Error Rate· 2023-09-18
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts Code
#2LPTSOTA
10
Error Rate· Augmentations· 2022-10-03
LPT: Long-tailed Prompt Tuning for Image Classification Code
#3VPTSOTA
15.2
Error Rate· Augmentations· 2022-03-23
Visual Prompt Tuning Code
#4LIFT (ViT-B/16, CLIP)
16.9
Error Rate· 2023-09-18
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts Code
#5GLMC + SAM
34.72
Error Rate· 2022-12-28
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data Code
#6GLMC (ResNet-34, channel x4)
36.15
Error Rate· 2023-05-15
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions Code
#7SURE(ResNet-32)
36.87
Error Rate· 2024-03-01
SURE: SUrvey REcipes for building reliable and robust deep networks Code
#8DeiT-LT
39.5
Error Rate· 2024-04-03
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets Code
#9MDCS
39.9
Error Rate· 2023-08-19
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition Code
#10OPeN (WideResNet-28-10)SOTA
40.2
Error Rate· 2021-12-16
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images Code
#11GML (ResNet-32)
41.9
Error Rate· 2023-05-02
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels Code
#12PC
42.25
Error Rate· 2023-02-01
Learning Prototype Classifiers for Long-Tailed Recognition Code
#13LTR-weight-balancing
42.29
Error Rate· 2022-03-27
Long-Tailed Recognition via Weight Balancing Code
#14ConCutMix
42.6
Error Rate· 2024-07-06
Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation Code
#15Difficulty-Net
43.1
Error Rate· 2022-09-07
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition Code
#16NCL(ResNet32)
43.2
Error Rate· 2022-03-29
Nested Collaborative Learning for Long-Tailed Visual Recognition Code
#17BCL(ResNet-32)
43.4
Error Rate· 2022-07-19
Balanced Contrastive Learning for Long-Tailed Visual Recognition Code
#18TADESOTA
46.1
Error Rate· 2021-07-20
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition Code
#19GCL
46.4
Error Rate· 2023-05-19
Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment Code
#20MiSLASSOTA
47.7
Error Rate· 2021-04-01
Improving Calibration for Long-Tailed Recognition Code
#21MetaSAug-LDAMSOTA
47.73
Error Rate· 2021-03-23
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition Code
#22CBD+TailCalibX
49.1
Error Rate· 2021-11-10
Feature Generation for Long-tail Classification Code
#23Hybrid-PSC
51.07
Error Rate· 2021-03-26
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
#24LDAM-DRW-RSG
51.5
Error Rate· 2021-06-18
RSG: A Simple but Effective Module for Learning Imbalanced Datasets Code
#25LDAM-DRW + SSPSOTA
52.89
Error Rate· 2020-06-13
Rethinking the Value of Labels for Improving Class-Imbalanced Learning Code