mlsanityData to 7 Oct 2026

Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation

arXiv 2203.00452 ↗First posted 28 Feb 2022cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG first learns a balanced and robust feature model with Gradual Balanced Loss, then fixes the feature model and augments the under-represented tail classes on the feature level with the knowledge from well-represented head classes. And the generated samples are mixed up with real training samples during training epochs. Gradual Balanced Loss is a general loss and it can combine with different decoupled training methods to improve the original performance. State-of-the-art results have been achieved on long-tail datasets such as CIFAR100-LT, ImageNetLT, and iNaturalist, which demonstrates the effectiveness of GLAG for long-tailed visual recognition.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 28 Feb 2022.

Builds on

35 of 43 references.

References · 35

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  4. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  6. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  7. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  8. 2020Long-tail learning via logit adjustmentcited by 605
  9. 2021Deep Long-Tailed Learning: A Surveycited by 416
  10. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  11. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  12. 2019A Baseline for Few-Shot Image Classificationcited by 298
23 more
  1. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  2. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  3. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  4. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  5. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  6. 2020Remix: Rebalanced Mixupcited by 144
  7. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  8. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  9. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  10. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  11. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  12. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  13. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  14. 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
  15. 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
  16. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  17. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  18. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 62
  19. 2021RSG: A Simple but Effective Module for Learning Imbalanced Datasetscited by 61
  20. 2019A Theoretical Analysis of the Number of Shots in Few-Shot Learningcited by 39
  21. 2021Label-Aware Distribution Calibration for Long-tailed Classificationcited by 13
  22. 2021Feature Generation for Long-tail Classificationcited by 9
  23. 2021Coarse-To-Fine Incremental Few-Shot Learningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2022A Pilot Study of Relating MYCN-Gene Amplification with Neuroblastoma-Patient CT Scanscited by 0
  2. 2026Class Confidence Aware Reweighting for Long Tailed Learningcited by 0