mlsanityData to 7 Oct 2026

A Systematic Review on Long-Tailed Learning

arXiv 2408.00483 ↗First posted 1 Aug 2024cs.LG cs.AI cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with long-tailed distributions, which can identify all the classes with high accuracy, in particular the minority/tail classes. It is a cutting-edge research direction that has attracted a remarkable amount of research effort in the past few years. In this paper, we present a comprehensive survey of latest advances in long-tailed visual learning. We first propose a new taxonomy for long-tailed learning, which consists of eight different dimensions, including data balancing, neural architecture, feature enrichment, logits adjustment, loss function, bells and whistles, network optimization, and post hoc processing techniques. Based on our proposed taxonomy, we present a systematic review of long-tailed learning methods, discussing their commonalities and alignable differences. We also analyze the differences between imbalance learning and long-tailed learning approaches. Finally, we discuss prospects and future directions in this field.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 156 of its 237 references that are in the map. First posted on arXiv 1 Aug 2024.

Builds on

156 of 237 references.

References · 156

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2017On Calibration of Modern Neural Networkscited by 4,860
  7. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  12. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
38 more
  1. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  2. 2016An overview of gradient descent optimization algorithmscited by 1,021
  3. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  4. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  5. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  6. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  7. 2019Modeling Tabular data using Conditional GANcited by 695
  8. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  9. 2020Long-tail learning via logit adjustmentcited by 605
  10. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  11. 2021Deep Long-Tailed Learning: A Surveycited by 416
  12. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  13. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  14. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  15. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  16. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  17. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
  18. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  19. 2021Parametric Contrastive Learningcited by 217
  20. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  21. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  22. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  23. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  24. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
  25. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  26. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  27. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  28. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  29. 2019What Do Compressed Deep Neural Networks Forget?cited by 164
  30. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  31. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  32. 2020Remix: Rebalanced Mixupcited by 144
  33. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  34. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143
  35. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  36. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  37. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  38. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130

50 most cited of 156 All 156 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 14.

27 papers.

Sort:

By area:

  1. 2025Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classificationcited by 14
  2. 2025From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibrationcited by 8
  3. 2026Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectoriecited by 5
  4. 2025Towards Practical Multi-label Causal Discovery in High-Dimensional Event Sequences via One-Shot Graph Aggregationcited by 4
  5. 2024Targeted Deep Learning System Boundary Testingcited by 3
  6. 2025Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruptioncited by 3
  7. 2025Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabelingcited by 3
  8. 2026Prototype Guided Post-pretraining for Single-Cell Representation Learningcited by 3
  9. 2025Enhancing Features in Long-tailed Data Using Large Vision Modelcited by 2
  10. 2025Emergent Specialization: Rare Token Neurons in Language Modelscited by 2
  11. 2025From Data to Knowledge: Evaluating How Efficiently Language Models Learn Factscited by 1
  12. 2025Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Conceptscited by 1
15 more
  1. 2025From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalizationcited by 1
  2. 2026REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspectivecited by 1
  3. 2024On the Inherent Robustness of One-Stage Object Detection against Out-of-Distribution Datacited by 0
  4. 2025Distributed Specialization: Rare-Token Neurons in Large Language Modelscited by 0
  5. 2026Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in Vehiclescited by 0
  6. 2026Neural Prior Estimation: Learning Class Priors from Latent Representationscited by 0
  7. 2026Dual-Imbalance Continual Learning for Real-World Food Recognitioncited by 0
  8. 2026CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learningcited by 0
  9. 2026Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignmentcited by 0
  10. 2026DA-UCT: Self-Supervised Domain-Adaptive Ultrasound Computed Tomography for Rapid Musculoskeletal Sound Speed Reconstructioncited by 0
  11. 2026Generalised Balanced Softmax: A Finite-Data Perspective on Logit Adjustment for Long-Tailed Recognitioncited by 0
  12. 2026GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignmentcited by 0
  13. 2026Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regressioncited by 0
  14. 2026Learning Under Forgetting: Statistical Support-Selective Retention in Stochastic Training Dynamicscited by 0
  15. 2026A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platformcited by 0