SOTAVerified

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

Showing 51100 of 131 papers

TitleStatusHype
Influence-Balanced Loss for Imbalanced Visual ClassificationCode1
Self Supervision to Distillation for Long-Tailed Visual RecognitionCode1
Parametric Contrastive LearningCode1
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed RecognitionCode1
RSG: A Simple but Effective Module for Learning Imbalanced DatasetsCode1
Class-Balanced Distillation for Long-Tailed Visual RecognitionCode1
Improving Calibration for Long-Tailed RecognitionCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual RecognitionCode1
ResLT: Residual Learning for Long-tailed RecognitionCode1
Disentangling Label Distribution for Long-tailed Visual RecognitionCode1
Class-Wise Difficulty-Balanced Loss for Solving Class-ImbalanceCode1
Long-tailed Recognition by Routing Diverse Distribution-Aware ExpertsCode1
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal EffectCode1
Balanced Meta-Softmax for Long-Tailed Visual RecognitionCode1
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed DatasetsCode1
Long-tail learning via logit adjustmentCode1
Rethinking the Value of Labels for Improving Class-Imbalanced LearningCode1
From Generalized zero-shot learning to long-tail with class descriptorsCode1
M2m: Imbalanced Classification via Major-to-minor TranslationCode1
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation PerspectiveCode1
Equalization Loss for Long-Tailed Object RecognitionCode1
Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed ClassificationCode1
Decoupling Representation and Classifier for Long-Tailed RecognitionCode1
Learning Imbalanced Datasets with Label-Distribution-Aware Margin LossCode1
Large-Scale Long-Tailed Recognition in an Open WorldCode1
Class-Balanced Loss Based on Effective Number of SamplesCode1
Mitigating Spurious Correlations with Causal Logit Perturbation0
LIFT+: Lightweight Fine-Tuning for Long-Tail LearningCode0
Learning from Neighbors: Category Extrapolation for Long-Tail Learning0
Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail LearningCode0
On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning0
Enhanced Long-Tailed Recognition with Contrastive CutMix AugmentationCode0
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail RecognitionCode0
Boosting Model Resilience via Implicit Adversarial Data Augmentation0
Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution0
Long-Tail Learning with Rebalanced Contrastive Loss0
Data-Centric Long-Tailed Image Recognition0
A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning. paper with codeCode0
Probability Guided Loss for Long-Tailed Multi-Label Image Classification0
Variance-Covariance Regularization Improves Representation Learning0
Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems0
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data0
Pseudo Labels Regularization for Imbalanced Partial-Label Learning0
Delving Deep into Simplicity Bias for Long-Tailed Image Recognition0
Weight-guided class complementing for long-tailed image recognition0
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics0
Learning Prototype Classifiers for Long-Tailed RecognitionCode0
Modeling the Distributional Uncertainty for Salient Object Detection Models0
Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach0
Show:102550
← PrevPage 2 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LIFT (ViT-L/14)Top-1 Accuracy82.9Unverified
2µ2Net+ (ViT-L/16)Top-1 Accuracy82.5Unverified
3MAM (ViT-B/16)Top-1 Accuracy82.3Unverified
4LIFT (ViT-B/16)Top-1 Accuracy78.3Unverified
5VL-LTR (ViT-B-16)Top-1 Accuracy77.2Unverified
6BALLAD(ResNet-50×16)Top-1 Accuracy76.5Unverified
7BALLAD(ViT-B-16)Top-1 Accuracy75.7Unverified
8BALLAD(ResNet-101)Top-1 Accuracy70.5Unverified
9VL-LTR (ResNet-50)Top-1 Accuracy70.1Unverified
10BALLAD(ResNet-50)Top-1 Accuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1Cross-Entropy (CE)Error Rate62.75Unverified
2Cross-Entropy (CE)Error Rate61.68Unverified
3IBLLossError Rate61.52Unverified
4Cross-Entropy + Curvature RegularizationError Rate59.5Unverified
5CE-DRWError Rate58.9Unverified
6LDAM-DRWError Rate57.96Unverified
7ELPError Rate57.6Unverified
8CDB-lossError Rate57.43Unverified
9CE-DRW-ICError Rate56.9Unverified
10LDAM-DRW + SSPError Rate56.57Unverified
#ModelMetricClaimedVerifiedStatus
1RISDAError Rate20.11Unverified
2Empirical Risk Minimization (ERM, CE)Error Rate13.61Unverified
3Class-balanced ReweightingError Rate13.46Unverified
4Class-balanced ResamplingError Rate13.21Unverified
5IBLLossError Rate12.93Unverified
6Class-balanced Focal LossError Rate12.9Unverified
7DecTDEError Rate12.63Unverified
8M2mError Rate12.5Unverified
9Prior-LTError Rate12.2Unverified
10ELF&LDAM+DRWError Rate12Unverified
#ModelMetricClaimedVerifiedStatus
1LIFT (ViT-L/14@336px)Top-1 Accuracy87.4Unverified
2LIFT (ViT-L/14)Top-1 Accuracy85.2Unverified
3GML (ViT-B-16)Top-1 Accuracy82.1Unverified
4LIFT (ViT-B/16)Top-1 Accuracy80.4Unverified
5RAC (ViT-B-16)Top-1 Accuracy80.24Unverified
6GPaCo (2-R152)Top-1 Accuracy79.8Unverified
7TADE(ResNet-152)Top-1 Accuracy77Unverified
8ProCo (ResNet50)Top-1 Accuracy75.8Unverified
9MDCS(Resnet50)Top-1 Accuracy75.6Unverified
10DeiT-LTTop-1 Accuracy75.1Unverified