Long-tail Learning

Long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing models from a large number of images that follow a long-tailed class distribution.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 131 papers

Title	Date	Tasks	Status	Hype
Mitigating Spurious Correlations with Causal Logit Perturbation	May 21, 2025	counterfactualLong-tail Learning	—Unverified	0
LIFT+: Lightweight Fine-Tuning for Long-Tail Learning	Apr 17, 2025	Data AugmentationLong-tail Learning	CodeCode Available	0
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition	Oct 28, 2024	Long-tail LearningVisual Prompt Tuning	CodeCode Available	1
Learning from Neighbors: Category Extrapolation for Long-Tail Learning	Oct 21, 2024	Long-tail LearningRepresentation Learning	—Unverified	0
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition	Oct 8, 2024	Contrastive LearningDensity Estimation	CodeCode Available	1
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation	Sep 30, 2024	Long-tail LearningSemantic Segmentation	CodeCode Available	1
Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning	Aug 20, 2024	ClassificationLong-tail Learning	CodeCode Available	0
LTRL: Boosting Long-tail Recognition via Reflective Learning	Jul 17, 2024	Long-tail Learning	CodeCode Available	1
On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning	Jul 13, 2024	Long-tail LearningPartial Label Learning	—Unverified	0
Adaptive Parametric Activation	Jul 11, 2024	imbalanced classificationInstance Segmentation	CodeCode Available	2

Show:10 25 50

← PrevPage 1 of 14Next →

All datasets ImageNet-LT CIFAR-100-LT (ρ=100)CIFAR-10-LT (ρ=10)iNaturalist 2018 CIFAR-100-LT (ρ=10)Places-LT CIFAR-10-LT (ρ=100)CIFAR-100-LT (ρ=50)MIMIC-CXR-LT NIH-CXR-LT COCO-MLT VOC-MLT

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ETF Classifier + DR (Resnet)	Error Rate	23.5	—	Unverified
2	LDAM-DRW	Error Rate	22.97	—	Unverified
3	LDAM-DRW + SSP	Error Rate	22.17	—	Unverified
4	ELP	Error Rate	22	—	Unverified
5	TSC(ResNet-32)	Error Rate	21.3	—	Unverified
6	CE+DRS+GIT	Error Rate	21.24	—	Unverified
7	smDRAGON	Error Rate	20.37	—	Unverified
8	TLC (4 experts)	Error Rate	19.6	—	Unverified
9	MetaSAug-LDAM	Error Rate	19.34	—	Unverified
10	ACE (4 experts)	Error Rate	18.6	—	Unverified