mlsanityData to 7 Oct 2026

Long-tailed Recognition by Routing Diverse Distribution-Aware Experts

arXiv 2010.01809 ↗First posted 5 Oct 2020cs.CVcited by 270

Not on the map. Why?

Abstract (arXiv)

Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over different data groups, resulting in increased tail accuracies but reduced head accuracies. We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail. We propose a new long-tailed classifier called RoutIng Diverse Experts (RIDE). It reduces the model variance with multiple experts, reduces the model bias with a distribution-aware diversity loss, reduces the computational cost with a dynamic expert routing module. RIDE outperforms the state-of-the-art by 5% to 7% on CIFAR100-LT, ImageNet-LT and iNaturalist 2018 benchmarks. It is also a universal framework that is applicable to various backbone networks, long-tailed algorithms, and training mechanisms for consistent performance gains. Our code is available at: https://github.com/frank-xwang/RIDE-LongTailRecognition.

Key facts. Cited by 270 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 61; 2023: 68; 2024: 53; 2025: 34; 2026: 24.

270 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2021Parametric Contrastive Learningcited by 217
  3. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143
  4. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  5. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  6. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 122
  7. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  8. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  9. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  10. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  11. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  12. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
38 more
  1. 2022Balanced MSE for Imbalanced Visual Regressioncited by 89
  2. 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
  3. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  4. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  5. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 78
  6. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  7. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  8. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  9. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  10. 2024A Touch, Vision, and Language Dataset for Multimodal Alignmentcited by 68
  11. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 66
  12. 2021VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognitioncited by 65
  13. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  14. 2022Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Featurescited by 63
  15. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  16. 2021DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learningcited by 51
  17. 2021Trustworthy Long-Tailed Classificationcited by 51
  18. 2021A Simple Long-Tailed Recognition Baseline via Vision-Language Modelcited by 49
  19. 2021Self-Damaging Contrastive Learningcited by 48
  20. 2022Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Studycited by 45
  21. 2022Generalized Parametric Contrastive Learningcited by 45
  22. 2022Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognitioncited by 44
  23. 2023Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitionscited by 43
  24. 2023Norm-guided latent space exploration for text-to-image generationcited by 43
  25. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  26. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  27. 2022Long-Tailed Class Incremental Learningcited by 36
  28. 2023How Re-sampling Helps for Long-Tail Learning?cited by 36
  29. 2021Robust Long-Tailed Learning under Label Noisecited by 35
  30. 2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
  31. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  32. 2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
  33. 2021Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognitioncited by 33
  34. 2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Contentcited by 33
  35. 2023ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognitioncited by 31
  36. 2022LTE4G: Long-Tail Experts for Graph Neural Networkscited by 30
  37. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  38. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30

50 most cited of 270 All 270 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Long-Tail Learning in Latent Space by sampling Synthetic Data
  2. 2023Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method
  3. 2022Diversified Dynamic Routing for Vision Tasks
  4. 2024Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
  5. 2023Class-Balancing Diffusion Models
  6. 2024Latent-based Diffusion Model for Long-tailed Recognition
  7. 2026Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning
  8. 2024AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction