mlsanityData to 7 Oct 2026

Class-Balanced Loss Based on Effective Number of Samples

arXiv 1901.05555 ↗First posted 16 Jan 2019cs.CVcited by 1,239

Not on the map. Why?

Cited by 22 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re-weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula (1-βn)/(1-β), where n is the number of samples and β ∈ [0,1) is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.

Key facts. Cited by 1,239 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 198; 2022: 207; 2023: 243; 2024: 196; 2025: 179; 2026: 216.

1,239 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  2. 2021Deep Long-Tailed Learning: A Surveycited by 416
  3. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  4. 2021IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoningcited by 262
  5. 2021BABEL: Bodies, Action and Behavior with English Labelscited by 261
  6. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  7. 2021Parametric Contrastive Learningcited by 217
  8. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  9. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  10. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  11. 2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 171
  12. 2021Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Trainingcited by 166
38 more
  1. 2021Delving into Deep Imbalanced Regressioncited by 157
  2. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143
  3. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  4. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  5. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  6. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  7. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  8. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 122
  9. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 114
  10. 2023In-Context Convergence of Transformerscited by 112
  11. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 108
  12. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  13. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  14. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 105
  15. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  16. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  17. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  18. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  19. 2021Learning to Predict Visual Attributes in the Wildcited by 95
  20. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  21. 2022Neural Collapse: A Review on Modelling Principles and Generalizationcited by 95
  22. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  23. 2021Influence-Balanced Loss for Imbalanced Visual Classificationcited by 91
  24. 2022Balanced MSE for Imbalanced Visual Regressioncited by 89
  25. 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
  26. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  27. 2022Learning Affordance Grounding from Exocentric Imagescited by 82
  28. 2021Detecting Human-Object Interaction via Fabricated Compositional Learningcited by 79
  29. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  30. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  31. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  32. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  33. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  34. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  35. 2023DELTA: degradation-free fully test-time adaptationcited by 72
  36. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  37. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  38. 2023Simple and Fast Group Robustness by Automatic Feature Reweightingcited by 68

50 most cited of 1,239 All 1,239 (JSON)