mlsanityData to 7 Oct 2026

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

arXiv 2007.08844 ↗First posted 17 Jul 2020cs.LG stat.MLcited by 105

Not on the map. Why?

Abstract (arXiv)

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from the biased model, and develop a simple algorithm, named Distribution Aligning Refinery of Pseudo-label (DARP) that solves it provably and efficiently. Under various class-imbalanced semi-supervised scenarios, we demonstrate the effectiveness of DARP and its compatibility with state-of-the-art SSL schemes.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 20; 2023: 33; 2024: 23; 2025: 8; 2026: 7.

105 papers.

Sort:

By area:

  1. 2021A Survey on Deep Semi-supervised Learningcited by 250
  2. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  3. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  4. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  5. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  6. 2022Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimationcited by 88
  7. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  8. 2021ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learningcited by 65
  9. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  10. 2021DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learningcited by 51
  11. 2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tablescited by 48
  12. 2021CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learningcited by 41
38 more
  1. 2021Self-supervised driven consistency training for annotation efficient histopathology image analysiscited by 39
  2. 2021Revisiting Consistency Regularization for Semi-Supervised Learningcited by 34
  3. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  4. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 30
  5. 2023Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessmentcited by 25
  6. 2023On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learningcited by 20
  7. 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learningcited by 19
  8. 2022Imbalanced Semi-supervised Learning with Bias Adaptive Classifiercited by 18
  9. 2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
  10. 2021Rethinking Re-Sampling in Imbalanced Semi-Supervised Learningcited by 16
  11. 2023Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learningcited by 16
  12. 2023Semi-Supervised Graph Imbalanced Regressioncited by 14
  13. 2024SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learningcited by 14
  14. 2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
  15. 2023Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learningcited by 13
  16. 2022An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learningcited by 12
  17. 2023InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learningcited by 12
  18. 2023Towards Semi-supervised Learning with Non-random Missing Labelscited by 12
  19. 2023Towards Distribution-Agnostic Generalized Category Discoverycited by 12
  20. 2021ACP++: Action Co-occurrence Priors for Human-Object Interaction Detectioncited by 11
  21. 2022On Non-Random Missing Labels in Semi-Supervised Learningcited by 11
  22. 2022Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Datacited by 11
  23. 2023Boosting Semi-Supervised Learning by bridging high and low-confidence predictionscited by 11
  24. 2022Semi-Supervised Temporal Action Detection with Proposal-Free Maskingcited by 10
  25. 2023RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Datacited by 10
  26. 2024Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognitioncited by 10
  27. 2022Transfer and Share: Semi-Supervised Learning from Long-Tailed Datacited by 9
  28. 2022SPADE: Semi-supervised Anomaly Detection under Distribution Mismatchcited by 9
  29. 2024BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learningcited by 9
  30. 2023SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learningcited by 8
  31. 2024Robust Semi-Supervised Learning in Open Environmentscited by 8
  32. 2021A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexitycited by 7
  33. 2023Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learningcited by 7
  34. 2023Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibrationcited by 7
  35. 2021An Empirical Study and Analysis on Open-Set Semi-Supervised Learningcited by 6
  36. 2021Single-Modal Entropy based Active Learning for Visual Question Answeringcited by 6
  37. 2022RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learningcited by 6
  38. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6

50 most cited of 105 All 105 (JSON)