mlsanityData to 7 Oct 2026

Deep Long-Tailed Learning: A Survey

arXiv 2110.04596 ↗First posted 9 Oct 2021cs.CVcited by 416

Not on the map. Why?

Abstract (arXiv)

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition. However, long-tailed class imbalance, a common problem in practical visual recognition tasks, often limits the practicality of deep network based recognition models in real-world applications, since they can be easily biased towards dominant classes and perform poorly on tail classes. To address this problem, a large number of studies have been conducted in recent years, making promising progress in the field of deep long-tailed learning. Considering the rapid evolution of this field, this paper aims to provide a comprehensive survey on recent advances in deep long-tailed learning. To be specific, we group existing deep long-tailed learning studies into three main categories (i.e., class re-balancing, information augmentation and module improvement), and review these methods following this taxonomy in detail. Afterward, we empirically analyze several state-of-the-art methods by evaluating to what extent they address the issue of class imbalance via a newly proposed evaluation metric, i.e., relative accuracy. We conclude the survey by highlighting important applications of deep long-tailed learning and identifying several promising directions for future research.

Key facts. Cited by 416 papers in the map (data through 7 Oct 2026). Builds on 128 of its 189 references that are in the map. First posted on arXiv 9 Oct 2021.

Builds on

128 of 189 references.

References · 128

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
38 more
  1. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  2. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  4. 2020Knowledge Distillation: A Surveycited by 1,578
  5. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  10. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  11. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  13. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  14. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  15. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  16. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  17. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  18. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  19. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  20. 2020Long-tail learning via logit adjustmentcited by 605
  21. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  22. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  23. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  24. 2018A Survey on Deep Transfer Learningcited by 417
  25. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  26. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  27. 2018Rethinking ImageNet Pre-trainingcited by 376
  28. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  29. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  30. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  31. 2020Rethinking Pre-training and Self-trainingcited by 352
  32. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  33. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  34. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  35. 2018Additive Margin Softmax for Face Verificationcited by 275
  36. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  37. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
  38. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256

50 most cited of 128 All 128 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 63; 2023: 85; 2024: 113; 2025: 74; 2026: 78.

416 papers.

Sort:

By area:

  1. 2023Class-Incremental Learning: A Surveycited by 209
  2. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  3. 2024OpenMoE: An Early Effort on Open Mixture-of-Experts Language Modelscited by 185
  4. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  5. 2022Diffusion Probabilistic Model Made Slimcited by 121
  6. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  7. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  8. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 78
  9. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  10. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  11. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  12. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 66
38 more
  1. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 65
  2. 2022Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Featurescited by 63
  3. 2022Expanding Small-Scale Datasets with Guided Imaginationcited by 61
  4. 2021A Simple Long-Tailed Recognition Baseline via Vision-Language Modelcited by 49
  5. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  6. 2022Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Studycited by 45
  7. 2022Towards Long-Tailed 3D Detectioncited by 40
  8. 2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
  9. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  10. 2023Beyond Normal: On the Evaluation of Mutual Information Estimatorscited by 37
  11. 2024Gradient Reweighting: Towards Imbalanced Class-Incremental Learningcited by 37
  12. 2023Disentangling Writer and Character Styles for Handwriting Generationcited by 35
  13. 2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
  14. 2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
  15. 2022Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptationcited by 33
  16. 2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Contentcited by 33
  17. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  18. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  19. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
  20. 2022A Survey on Video Action Recognition in Sports: Datasets, Methods and Applicationscited by 27
  21. 2023Understanding and Mitigating the Label Noise in Pre-training on Downstream Taskscited by 27
  22. 2024A Systematic Review on Long-Tailed Learningcited by 27
  23. 2022On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyondcited by 26
  24. 2022Contrastive Learning with Boosted Memorizationcited by 26
  25. 2023Dynamic Residual Classifier for Class Incremental Learningcited by 26
  26. 2024Playable Game Generationcited by 26
  27. 2022ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classificationcited by 25
  28. 2022CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learningcited by 24
  29. 2023Class-Imbalanced Learning on Graphs: A Surveycited by 24
  30. 2023A Unified Perspective for Loss-Oriented Imbalanced Learning via Localizationcited by 24
  31. 2023ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordinationcited by 23
  32. 2022Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehiclescited by 22
  33. 2022Boosting Offline Reinforcement Learning via Data Rebalancingcited by 22
  34. 2022Delving into Semantic Scale Imbalancecited by 22
  35. 2023Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challengecited by 22
  36. 2022ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classificationcited by 21
  37. 2022A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processingcited by 20
  38. 2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20

50 most cited of 416 All 416 (JSON)