mlsanityData to 14 Oct 2026

DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning

arXiv 2106.05682 ↗First posted 10 Jun 2021cs.CV cs.AI cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). Builds on 50 of its 75 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

50 of 75 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2016Wide Residual Networkscited by 3,070
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  12. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
38 more
  1. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  2. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  4. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  7. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  8. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  9. 2020Long-tail learning via logit adjustmentcited by 618
  10. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  11. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  12. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  13. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  14. 2020Meta Pseudo Labelscited by 374
  15. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  16. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  17. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  18. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  19. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  20. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  21. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  22. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  23. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  24. 2020Detecting Human-Object Interactions with Action Co-occurrence Priorscited by 72
  25. 2020MoPro: Webly Supervised Learning with Momentum Prototypescited by 66
  26. 2018Imbalanced Deep Learning by Minority Class Incremental Rectificationcited by 65
  27. 2017Deep Over-sampling Framework for Classifying Imbalanced Datacited by 59
  28. 2020FeatMatch: Feature-Based Augmentation for Semi-Supervised Learningcited by 57
  29. 2020Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learningcited by 53
  30. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
  31. 2019Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approachcited by 30
  32. 2020Class-Imbalanced Semi-Supervised Learningcited by 28
  33. 2021The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshopcited by 21
  34. 2018Disjoint Multi-task Learning between Heterogeneous Human-centric Taskscited by 16
  35. 2020Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learningcited by 14
  36. 2021Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillationcited by 14
  37. 2019SelectNet: Learning to Sample from the Wild for Imbalanced Data Trainingcited by 3
  38. 2020Building One-Shot Semi-supervised (BOSS) Learning up to Fully Supervised Performancecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 10; 2024: 21; 2025: 9; 2026: 4.

51 papers.

Sort:

By area:

  1. 2022Debiased Self-Training for Semi-Supervised Learningcited by 62
  2. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  3. 2023Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentationcited by 35
  4. 2024A Systematic Review on Long-Tailed Learningcited by 28
  5. 2022Imbalanced Semi-supervised Learning with Bias Adaptive Classifiercited by 18
  6. 2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
  7. 2022Generative Bias for Robust Visual Question Answeringcited by 12
  8. 2022An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learningcited by 12
  9. 2023InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learningcited by 12
  10. 2024CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learningcited by 10
  11. 2024Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognitioncited by 10
  12. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
38 more
  1. 2022Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognitioncited by 8
  2. 2022MultiMatch: Multi-task Learning for Semi-supervised Domain Generalizationcited by 7
  3. 2023Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibrationcited by 7
  4. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  5. 2024BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learningcited by 6
  6. 2025Prediction-Powered Semi-Supervised Learning with Online Power Tuningcited by 5
  7. 2023Semi-Supervised Image Captioning by Adversarially Propagating Labeled Datacited by 4
  8. 2023SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classificationcited by 4
  9. 2023UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detectioncited by 3
  10. 2024Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detectioncited by 3
  11. 2024AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learningcited by 3
  12. 2025Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Modelscited by 3
  13. 2024Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectivescited by 2
  14. 2024Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Datacited by 2
  15. 2023NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learningcited by 1
  16. 2024IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Taskscited by 1
  17. 2024Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learningcited by 1
  18. 2025Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learningcited by 1
  19. 2025Sampling Control for Imbalanced Calibration in Semi-Supervised Learningcited by 1
  20. 2026Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridgescited by 1
  21. 2026When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labelingcited by 1
  22. 2022Land Cover and Land Use Detection using Semi-Supervised Learningcited by 0
  23. 2023BMB: Balanced Memory Bank for Imbalanced Semi-supervised Learningcited by 0
  24. 2023CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learningcited by 0
  25. 2024Uncertainty-aware Sampling for Long-tailed Semi-supervised Learningcited by 0
  26. 2024VCC-INFUSE: Towards Accurate and Efficient Selection of Unlabeled Examples in Semi-supervised Learningcited by 0
  27. 2024Incremental Self-training for Semi-supervised Learningcited by 0
  28. 2024Towards Realistic Long-tailed Semi-supervised Learning in an Open Worldcited by 0
  29. 2024Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustmentcited by 0
  30. 2024Learning Unlabeled Clients Divergence for Federated Semi-Supervised Learning via Anchor Model Aggregationcited by 0
  31. 2024Image-Feature Weak-to-Strong Consistency: An Enhanced Paradigm for Semi-Supervised Learningcited by 0
  32. 2024CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News Detectioncited by 0
  33. 2024Energy Score-based Pseudo-Label Filtering and Adaptive Loss for Imbalanced Semi-supervised SAR target recognitioncited by 0
  34. 2025SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examplescited by 0
  35. 2025ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learningcited by 0
  36. 2025Enhancing Classification with Semi-Supervised Deep Learning Using Distance-Based Sample Weightscited by 0
  37. 2025ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Datacited by 0
  38. 2026Semi-Supervised Hyperspectral Image Classification with Edge-Aware Superpixel Label Propagation and Adaptive Pseudo-Labelingcited by 0

50 most cited of 51 All 51 (JSON)