mlsanityData to 14 Oct 2026

RSG: A Simple but Effective Module for Learning Imbalanced Datasets

arXiv 2106.09859 ↗First posted 18 Jun 2021cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

Imbalanced datasets widely exist in practice and area great challenge for training deep neural models with agood generalization on infrequent classes. In this work, wepropose a new rare-class sample generator (RSG) to solvethis problem. RSG aims to generate some new samplesfor rare classes during training, and it has in particularthe following advantages: (1) it is convenient to use andhighly versatile, because it can be easily integrated intoany kind of convolutional neural network, and it works wellwhen combined with different loss functions, and (2) it isonly used during the training phase, and therefore, no ad-ditional burden is imposed on deep neural networks duringthe testing phase. In extensive experimental evaluations, weverify the effectiveness of RSG. Furthermore, by leveragingRSG, we obtain competitive results on Imbalanced CIFARand new state-of-the-art results on Places-LT, ImageNet-LT, and iNaturalist 2018. The source code is available at https://github.com/Jianf-Wang/RSG.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 18 Jun 2021.

Builds on

26 of 39 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  9. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  10. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  11. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  12. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
14 more
  1. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  2. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  3. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  4. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  5. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  6. 2018Additive Margin Softmax for Face Verificationcited by 278
  7. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  8. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  9. 2018Low-Shot Learning from Imaginary Datacited by 181
  10. 2018Gradient Harmonized Single-stage Detectorcited by 114
  11. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111
  12. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 91
  13. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  14. 2021Convolutional Neural Networks with Gated Recurrent Connectionscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 25; 2024: 9; 2025: 8; 2026: 7.

61 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2023Class-Balancing Diffusion Modelscited by 48
  3. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  4. 2023Exploring Vision-Language Models for Imbalanced Learningcited by 35
  5. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  6. 2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
  7. 2024A Systematic Review on Long-Tailed Learningcited by 28
  8. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  9. 2023Long-Tailed Partial Label Learning via Dynamic Rebalancingcited by 22
  10. 2023Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavationcited by 22
  11. 2023GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classificationcited by 19
  12. 2021Margin Calibration for Long-Tailed Visual Recognitioncited by 17
38 more
  1. 2023GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classificationcited by 17
  2. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  3. 2021Long-tail Recognition via Compositional Knowledge Transfercited by 16
  4. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  5. 2025Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Datacited by 15
  6. 2023Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decompositioncited by 13
  7. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  8. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  9. 2025Long-tailed Recognition with Model Rebalancingcited by 10
  10. 2023Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifoldscited by 9
  11. 2023SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tailcited by 9
  12. 2025Improved Balanced Classification with Theoretically Grounded Loss Functionscited by 9
  13. 2023Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognitioncited by 7
  14. 2023Exploring Weight Balancing on Long-Tailed Recognition Problemcited by 7
  15. 2022Inverse Image Frequency for Long-tailed Image Recognitioncited by 6
  16. 2024Training Class-Imbalanced Diffusion Model Via Overlap Optimizationcited by 6
  17. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  18. 2025Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Modelcited by 6
  19. 2023Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learningcited by 5
  20. 2022Rebalanced Siamese Contrastive Mining for Long-Tailed Recognitioncited by 4
  21. 2022Personalizing Intervened Network for Long-tailed Sequential User Behavior Modelingcited by 4
  22. 2023Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognitioncited by 3
  23. 2024MONICA: Benchmarking on Long-tailed Medical Image Classificationcited by 3
  24. 2022Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generationcited by 2
  25. 2023MvCo-DoT:Multi-View Contrastive Domain Transfer Network for Medical Report Generationcited by 2
  26. 2023Dual Compensation Residual Networks for Class Imbalanced Learningcited by 2
  27. 2024Prior2Posterior: Model Prior Correction for Long-Tailed Learningcited by 2
  28. 2025Classifying Long-tailed and Label-noise Data via Disentangling and Unlearningcited by 2
  29. 2026Optimized Deferral for Imbalanced Settingscited by 2
  30. 2022Teacher Guided Training: An Efficient Framework for Knowledge Transfercited by 1
  31. 2023NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learningcited by 1
  32. 2023MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentationcited by 1
  33. 2023Towards Effective Collaborative Learning in Long-Tailed Recognitioncited by 1
  34. 2023Ensemble Modeling for Multimodal Visual Action Recognitioncited by 1
  35. 2024Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustmentcited by 1
  36. 2024Revisiting Long-Tailed Learning: Insights from an Architectural Perspectivecited by 1
  37. 2023Multi-Head Feature Pyramid Networks for Breast Mass Detectioncited by 0
  38. 2023A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognitioncited by 0

50 most cited of 61 All 61 (JSON)