mlsanityData to 14 Oct 2026

Semi-Supervised Semantic Segmentation with Cross-Consistency Training

arXiv 2003.09005 ↗First posted 19 Mar 2020cs.CVcited by 376

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the cluster assumption, in which the decision boundary should lie in low-density regions. In this work, we first observe that for semantic segmentation, the low-density regions are more apparent within the hidden representations than within the inputs. We thus propose cross-consistency training, where an invariance of the predictions is enforced over different perturbations applied to the outputs of the encoder. Concretely, a shared encoder and a main decoder are trained in a supervised manner using the available labeled examples. To leverage the unlabeled examples, we enforce a consistency between the main decoder predictions and those of the auxiliary decoders, taking as inputs different perturbed versions of the encoder's output, and consequently, improving the encoder's representations. The proposed method is simple and can easily be extended to use additional training signal, such as image-level labels or pixel-level labels across different domains. We perform an ablation study to tease apart the effectiveness of each component, and conduct extensive experiments to demonstrate that our method achieves state-of-the-art results in several datasets.

Key facts. Cited by 376 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 61; 2022: 83; 2023: 86; 2024: 70; 2025: 54; 2026: 22.

376 papers.

Sort:

By area:

  1. 2021Extract Free Dense Labels from CLIPcited by 583
  2. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  3. 2021A Survey on Deep Semi-supervised Learningcited by 251
  4. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  5. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  6. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  7. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  8. 2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 117
  9. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  10. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  11. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 108
  12. 2021Semi-supervised Left Atrium Segmentation with Mutual Consistency Trainingcited by 104
38 more
  1. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  2. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  3. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 100
  4. 2023Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervisioncited by 99
  5. 2022Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentationcited by 93
  6. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 93
  7. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  8. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  9. 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
  10. 2021A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentationcited by 79
  11. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  12. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 76
  13. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  14. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  15. 2022CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervisioncited by 64
  16. 2022Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervisioncited by 64
  17. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  18. 2021Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentationcited by 61
  19. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  20. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  21. 2022Unsupervised Salient Object Detection with Spectral Cluster Votingcited by 56
  22. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  23. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 54
  24. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 54
  25. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  26. 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50
  27. 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 49
  28. 2021ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenescited by 47
  29. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  30. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 44
  31. 2023Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspectivecited by 43
  32. 2025BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster responsecited by 41
  33. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  34. 2022Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentationcited by 40
  35. 2023VDD: Varied Drone Dataset for Semantic Segmentationcited by 40
  36. 2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
  37. 2023Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentationcited by 35
  38. 2023Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentationcited by 35

50 most cited of 376 All 376 (JSON)