mlsanityData to 7 Oct 2026

CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

arXiv 2102.09559 ↗First posted 18 Feb 2021cs.CVcited by 174

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied. While existing semi-supervised learning (SSL) methods are known to perform poorly on minority classes, we find that they still generate high precision pseudo-labels on minority classes. By exploiting this property, in this work, we propose Class-Rebalancing Self-Training (CReST), a simple yet effective framework to improve existing SSL methods on class-imbalanced data. CReST iteratively retrains a baseline SSL model with a labeled set expanded by adding pseudo-labeled samples from an unlabeled set, where pseudo-labeled samples from minority classes are selected more frequently according to an estimated class distribution. We also propose a progressive distribution alignment to adaptively adjust the rebalancing strength dubbed CReST+. We show that CReST and CReST+ improve state-of-the-art SSL algorithms on various class-imbalanced datasets and consistently outperform other popular rebalancing methods. Code has been made available at https://github.com/google-research/crest.

Key facts. Cited by 174 papers in the map (data through 7 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 18 Feb 2021.

Builds on

37 of 53 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2016Wide Residual Networkscited by 3,057
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  8. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  9. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  10. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
25 more
  1. 2016Deep Networks with Stochastic Depthcited by 973
  2. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  5. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  6. 2020Long-tail learning via logit adjustmentcited by 605
  7. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  8. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  9. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  10. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  11. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  12. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
  13. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  14. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  15. 2016What makes ImageNet good for transfer learning?cited by 192
  16. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  17. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  18. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  19. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  20. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  21. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  22. 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
  23. 2018Improving Generalization via Scalable Neighborhood Component Analysiscited by 53
  24. 2020Class-Imbalanced Semi-Supervised Learningcited by 28
  25. 2020Correcting Data Imbalance for Semi-Supervised Covid-19 Detection Using X-ray Chest Imagescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 33; 2023: 54; 2024: 42; 2025: 20; 2026: 13.

174 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  3. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  4. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  5. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  6. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  7. 2022Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimationcited by 88
  8. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  9. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  10. 2021ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learningcited by 65
  11. 2021DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learningcited by 51
  12. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
38 more
  1. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  2. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  3. 2021Structured Sparse R-CNN for Direct Scene Graph Generationcited by 44
  4. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  5. 2021CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learningcited by 41
  6. 2022TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learningcited by 35
  7. 2023Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentationcited by 35
  8. 2021Revisiting Consistency Regularization for Semi-Supervised Learningcited by 34
  9. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  10. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  11. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  12. 2023RLSbench: Domain Adaptation Under Relaxed Label Shiftcited by 30
  13. 2021Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Trainingcited by 28
  14. 2024A Systematic Review on Long-Tailed Learningcited by 27
  15. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  16. 2022ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classificationcited by 25
  17. 2023DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentationcited by 25
  18. 2022ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classificationcited by 21
  19. 2022Fuzzy Positive Learning for Semi-supervised Semantic Segmentationcited by 19
  20. 2023GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classificationcited by 19
  21. 2022Imbalanced Semi-supervised Learning with Bias Adaptive Classifiercited by 18
  22. 2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
  23. 2021Rethinking Re-Sampling in Imbalanced Semi-Supervised Learningcited by 16
  24. 2021Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Imagescited by 16
  25. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
  26. 2023DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detectioncited by 16
  27. 2023Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learningcited by 16
  28. 2022Masked Unsupervised Self-training for Label-free Image Classificationcited by 14
  29. 2023Semi-Supervised Graph Imbalanced Regressioncited by 14
  30. 2024SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learningcited by 14
  31. 2022Class-Level Confidence Based 3D Semi-Supervised Learningcited by 13
  32. 2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
  33. 2023FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labelscited by 13
  34. 2023Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learningcited by 13
  35. 2024P2OT: Progressive Partial Optimal Transport for Deep Imbalanced Clusteringcited by 13
  36. 2022An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learningcited by 12
  37. 2023InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learningcited by 12
  38. 2023Towards Semi-supervised Learning with Non-random Missing Labelscited by 12

50 most cited of 174 All 174 (JSON)