mlsanityData to 14 Oct 2026

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

arXiv 1912.02413 ↗First posted 5 Dec 2019cs.CV cs.LGcited by 403

Not on the map. Why?

Abstract (arXiv)

Our work focuses on tackling the challenging but natural visual recognition task of long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples). In the literature, class re-balancing strategies (e.g., re-weighting and re-sampling) are the prominent and effective methods proposed to alleviate the extreme imbalance for dealing with long-tailed problems. In this paper, we firstly discover that these re-balancing methods achieving satisfactory recognition accuracy owe to that they could significantly promote the classifier learning of deep networks. However, at the same time, they will unexpectedly damage the representative ability of the learned deep features to some extent. Therefore, we propose a unified Bilateral-Branch Network (BBN) to take care of both representation learning and classifier learning simultaneously, where each branch does perform its own duty separately. In particular, our BBN model is further equipped with a novel cumulative learning strategy, which is designed to first learn the universal patterns and then pay attention to the tail data gradually. Extensive experiments on four benchmark datasets, including the large-scale iNaturalist ones, justify that the proposed BBN can significantly outperform state-of-the-art methods. Furthermore, validation experiments can demonstrate both our preliminary discovery and effectiveness of tailored designs in BBN for long-tailed problems. Our method won the first place in the iNaturalist 2019 large scale species classification competition, and our code is open-source and available at https://github.com/Megvii-Nanjing/BBN.

Key facts. Cited by 403 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 84; 2022: 88; 2023: 79; 2024: 84; 2025: 39; 2026: 29.

403 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2021Parametric Contrastive Learningcited by 217
  3. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  4. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  5. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  6. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
  7. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  8. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  9. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  10. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  11. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  12. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
38 more
  1. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  2. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  3. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  4. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  5. 2021Medical Visual Question Answering: A Surveycited by 93
  6. 2022Balanced MSE for Imbalanced Visual Regressioncited by 89
  7. 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
  8. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  9. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  10. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  11. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  12. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  13. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  14. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  15. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  16. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  17. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 67
  18. 2021Learning of Visual Relations: The Devil is in the Tailscited by 65
  19. 2021VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognitioncited by 65
  20. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 64
  21. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  22. 2021RSG: A Simple but Effective Module for Learning Imbalanced Datasetscited by 61
  23. 2021Learning Representation for Clustering via Prototype Scattering and Positive Samplingcited by 58
  24. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  25. 2021DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learningcited by 51
  26. 2021Trustworthy Long-Tailed Classificationcited by 51
  27. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  28. 2021A Simple Long-Tailed Recognition Baseline via Vision-Language Modelcited by 49
  29. 2022AutoBalance: Optimized Loss Functions for Imbalanced Datacited by 49
  30. 2022Generalized Parametric Contrastive Learningcited by 45
  31. 2022Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognitioncited by 44
  32. 2022Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learningcited by 43
  33. 2023Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitionscited by 43
  34. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  35. 2021CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learningcited by 41
  36. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  37. 2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
  38. 2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38

50 most cited of 403 All 403 (JSON)