mlsanityData to 14 Oct 2026

The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification

arXiv 2112.00412 ↗First posted 1 Dec 2021cs.CV cs.AIcited by 100

Not on the map. Why?

Abstract (arXiv)

The problem of class imbalanced data is that the generalization performance of the classifier deteriorates due to the lack of data from minority classes. In this paper, we propose a novel minority over-sampling method to augment diversified minority samples by leveraging the rich context of the majority classes as background images. To diversify the minority samples, our key idea is to paste an image from a minority class onto rich-context images from a majority class, using them as background images. Our method is simple and can be easily combined with the existing long-tailed recognition methods. We empirically prove the effectiveness of the proposed oversampling method through extensive experiments and ablation studies. Without any architectural changes or complex algorithms, our method achieves state-of-the-art performance on various long-tailed classification benchmarks. Our code is made available at https://github.com/naver-ai/cmo.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). Builds on 37 of its 59 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

37 of 59 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  8. 2016Wide Residual Networkscited by 3,070
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  11. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  12. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
25 more
  1. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  2. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  5. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  6. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  7. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  8. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  9. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  10. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  11. 2021Parametric Contrastive Learningcited by 217
  12. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  13. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  14. 2019Seeing What a GAN Cannot Generatecited by 148
  15. 2020Remix: Rebalanced Mixupcited by 144
  16. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  17. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  18. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  19. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  20. 2021Influence-Balanced Loss for Imbalanced Visual Classificationcited by 91
  21. 2019Generative Adversarial Minority Oversamplingcited by 73
  22. 2018NSML: Meet the MLaaS platform with a real-world case studycited by 70
  23. 2017Deep Over-sampling Framework for Classifying Imbalanced Datacited by 59
  24. 2018Deep Imbalanced Attribute Classification using Visual Attention Aggregationcited by 56
  25. 2018Improved Mixed-Example Data Augmentationcited by 42

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 37; 2024: 27; 2025: 19; 2026: 10.

100 papers.

Sort:

By area:

  1. 2023Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurtscited by 58
  2. 2023Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitionscited by 43
  3. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  4. 2024Gradient Reweighting: Towards Imbalanced Class-Incremental Learningcited by 37
  5. 2023How Re-sampling Helps for Long-Tail Learning?cited by 36
  6. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  7. 2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
  8. 2024Enhance Image Classification via Inter-Class Image Mixup with Diffusion Modelcited by 34
  9. 2023Feedback-guided Data Synthesis for Imbalanced Classificationcited by 33
  10. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  11. 2024A Systematic Review on Long-Tailed Learningcited by 28
  12. 2023Use Your Head: Improving Long-Tail Video Recognitioncited by 22
38 more
  1. 2023Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavationcited by 22
  2. 2022Balanced Product of Calibrated Experts for Long-Tailed Recognitioncited by 20
  3. 2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20
  4. 2023Long-Tailed Continual Learning For Visual Food Recognitioncited by 20
  5. 2022Long-tailed Food Classificationcited by 19
  6. 2023MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognitioncited by 19
  7. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  8. 2023EAT: Towards Long-Tailed Out-of-Distribution Detectioncited by 16
  9. 2024Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuningcited by 15
  10. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  11. 2023No One Left Behind: Improving the Worst Categories in Long-Tailed Learningcited by 14
  12. 2024Latent-based Diffusion Model for Long-tailed Recognitioncited by 14
  13. 2023Decoupled Training for Long-Tailed Classification With Stochastic Representationscited by 13
  14. 2023SYNAuG: Exploiting Synthetic Data for Data Imbalance Problemscited by 13
  15. 2023Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noisecited by 11
  16. 2024Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classificationcited by 11
  17. 2023Generative Oversampling for Imbalanced Data via Majority-Guided VAEcited by 10
  18. 2023Single-Stage Heavy-Tailed Food Classificationcited by 10
  19. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  20. 2023Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifoldscited by 9
  21. 2023SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tailcited by 9
  22. 2023Deep Imbalanced Regression via Hierarchical Classification Adjustmentcited by 9
  23. 2024Learning from Neighbors: Category Extrapolation for Long-Tail Learningcited by 9
  24. 2024Difficulty-aware Balancing Margin Loss for Long-tailed Recognitioncited by 9
  25. 2024DELTA: Decoupling Long-Tailed Online Continual Learningcited by 8
  26. 2023Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibrationcited by 7
  27. 2023RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classificationcited by 7
  28. 2023SCoRe: Submodular Combinatorial Representation Learningcited by 7
  29. 2024Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentationcited by 7
  30. 2022DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognitioncited by 6
  31. 2022Inverse Image Frequency for Long-tailed Image Recognitioncited by 6
  32. 2022Dynamic Loss For Robust Learningcited by 6
  33. 2024How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalancecited by 6
  34. 2024BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learningcited by 6
  35. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  36. 2023Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learningcited by 5
  37. 2024Fractal Calibration for long-tailed object detectioncited by 5
  38. 2025LIFT+: Lightweight Fine-Tuning for Long-Tail Learningcited by 5

50 most cited of 100 All 100 (JSON)