mlsanityData to 14 Oct 2026

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

arXiv 2106.01226 ↗First posted 2 Jun 2021cs.CVcited by 463

Not on the map. Why?

Cited by 24 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012. Code is available at https://git.io/CPS.

Key facts. Cited by 463 papers in the map (data through 14 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

32 of 43 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  8. 2016Pyramid Scene Parsing Networkcited by 2,479
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  12. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
20 more
  1. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  2. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  4. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  5. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  6. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  7. 2019PointRend: Image Segmentation as Renderingcited by 440
  8. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  9. 2020Rethinking Pre-training and Self-trainingcited by 352
  10. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  11. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  12. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 166
  13. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  14. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  15. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  16. 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 104
  17. 2020SegFix: Model-Agnostic Boundary Refinement for Segmentationcited by 97
  18. 2020Structured Consistency Loss for semi-supervised semantic segmentationcited by 40
  19. 2018Semi-Supervised Semantic Image Segmentation with Self-correcting Networkscited by 37
  20. 2020Improving Semantic Segmentation via Self-Trainingcited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 89; 2023: 117; 2024: 93; 2025: 92; 2026: 48.

463 papers.

Sort:

By area:

  1. 2022Large Language Models Can Self-Improvecited by 664
  2. 2021Extract Free Dense Labels from CLIPcited by 583
  3. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  4. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  5. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  6. 2022ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentationcited by 178
  7. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  8. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  9. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 113
  10. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 108
  11. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  12. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 100
38 more
  1. 2023Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervisioncited by 99
  2. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 93
  3. 2021SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentationcited by 86
  4. 2022Self-Training: A Surveycited by 86
  5. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  6. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  7. 2023Language Model Self-improvement by Reinforcement Learning Contemplationcited by 75
  8. 2022SVFormer: Semi-supervised Video Transformer for Action Recognitioncited by 68
  9. 2022Unsupervised Object Localization: Observing the Background to Discover Objectscited by 66
  10. 2022Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervisioncited by 64
  11. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  12. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  13. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 54
  14. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 54
  15. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  16. 2022Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentationcited by 51
  17. 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50
  18. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  19. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  20. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 44
  21. 2023Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspectivecited by 43
  22. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  23. 2023SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidancecited by 41
  24. 2025BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster responsecited by 41
  25. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  26. 2023VDD: Varied Drone Dataset for Semantic Segmentationcited by 40
  27. 2023DreamTeacher: Pretraining Image Backbones with Deep Generative Modelscited by 37
  28. 2023Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentationcited by 35
  29. 2023Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentationcited by 35
  30. 2024AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentationcited by 35
  31. 2023Semi-Supervised Semantic Segmentation via Gentle Teaching Assistantcited by 34
  32. 2021Reference-guided Pseudo-Label Generation for Medical Semantic Segmentationcited by 33
  33. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  34. 2023ProtoSeg: Interpretable Semantic Segmentation with Prototypical Partscited by 33
  35. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  36. 2022RSCFed: Random Sampling Consensus Federated Semi-supervised Learningcited by 32
  37. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  38. 2021Data-Free Knowledge Transfer: A Surveycited by 31

50 most cited of 463 All 463 (JSON)