mlsanityData to 14 Oct 2026

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

arXiv 2107.11279 ↗First posted 23 Jul 2021cs.CVcited by 78

Not on the map. Why?

Abstract (arXiv)

While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic segmentation datasets that make the pseudo-labeled data bias toward majority classes. In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data. Besides, we also contribute a progressive data augmentation and labeling strategy to facilitate model training with pseudo-labeled data. Experiments on both Cityscapes and PASCAL VOC 2012 datasets demonstrate the effectiveness of our approach. Albeit simple, our method performs favorably in comparison with state-of-the-art approaches. Code will be available at https://github.com/CVMI-Lab/DARS.

Key facts. Cited by 78 papers in the map (data through 14 Oct 2026). Builds on 55 of its 69 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

55 of 69 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2017On Calibration of Modern Neural Networkscited by 4,960
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  11. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  12. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
38 more
  1. 2016Pyramid Scene Parsing Networkcited by 2,479
  2. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  3. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  4. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  6. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  7. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  9. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  10. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  13. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  14. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  15. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  16. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  17. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  18. 2019Confidence Regularized Self-Trainingcited by 419
  19. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  20. 2020Rethinking Pre-training and Self-trainingcited by 352
  21. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  22. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  23. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  24. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  25. 2015ParseNet: Looking Wider to See Bettercited by 177
  26. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  27. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  28. 2017Understanding Convolution for Semantic Segmentationcited by 168
  29. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  30. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  31. 2018Pyramid Attention Network for Semantic Segmentationcited by 149
  32. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  33. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  34. 2020Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learningcited by 105
  35. 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 104
  36. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  37. 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
  38. 2018Imbalanced Deep Learning by Minority Class Incremental Rectificationcited by 65

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 26; 2023: 19; 2024: 12; 2025: 11; 2026: 4.

78 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  3. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  4. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  5. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  6. 2022Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoningcited by 92
  7. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  8. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  9. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 57
  10. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  11. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 54
  12. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
38 more
  1. 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50
  2. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  3. 2023SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidancecited by 41
  4. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  5. 2022Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentationcited by 30
  6. 2022CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detectioncited by 27
  7. 2023Semantic Image Segmentation: Two Decades of Researchcited by 27
  8. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  9. 2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26
  10. 2022Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?cited by 21
  11. 2023The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representationcited by 21
  12. 2022Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentationcited by 17
  13. 2023A Survey on Semi-Supervised Semantic Segmentationcited by 17
  14. 2024Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentationcited by 16
  15. 2022Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learningcited by 15
  16. 2022DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentationcited by 13
  17. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  18. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  19. 2022Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentationcited by 12
  20. 2022Semi-supervised Semantic Segmentation with Mutual Knowledge Distillationcited by 12
  21. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  22. 2024RESMatch: Referring Expression Segmentation in a Semi-Supervised Mannercited by 11
  23. 2022MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopycited by 10
  24. 2023SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tailcited by 9
  25. 2023Active Learning for Semantic Segmentation with Multi-class Label Querycited by 9
  26. 2023Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentationcited by 8
  27. 2022VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditionscited by 7
  28. 20232D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentationcited by 6
  29. 2023Semi-Supervised Active Learning for Semantic Segmentation in Unknown Environments Using Informative Path Planningcited by 6
  30. 2024BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learningcited by 6
  31. 2025MetaSSL: A General Heterogeneous Loss for Semi-Supervised Medical Image Segmentationcited by 6
  32. 2025When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentationcited by 6
  33. 2024An Evidential-enhanced Tri-Branch Consistency Learning Method for Semi-supervised Medical Image Segmentationcited by 5
  34. 2024Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Studycited by 5
  35. 2023CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentationcited by 4
  36. 2021Semi-supervised Salient Object Detection with Effective Confidence Estimationcited by 3
  37. 2022Progressive Learning with Cross-Window Consistency for Semi-Supervised Semantic Segmentationcited by 3
  38. 2022Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentationcited by 3

50 most cited of 78 All 78 (JSON)