mlsanityData to 7 Oct 2026

Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation

arXiv 2108.09025 ↗First posted 20 Aug 2021cs.CVcited by 101

Not on the map. Why?

Abstract (arXiv)

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.

Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). Builds on 49 of its 58 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

49 of 58 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  10. 2020Supervised Contrastive Learningcited by 2,803
  11. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  12. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
37 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  3. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  6. 2019Contrastive Multiview Codingcited by 1,297
  7. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  8. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  9. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  10. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  11. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  12. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  13. 2020Debiased Contrastive Learningcited by 354
  14. 2020Rethinking Pre-training and Self-trainingcited by 352
  15. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  16. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  17. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  18. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
  19. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  20. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  21. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  22. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  23. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 205
  24. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  25. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  26. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  27. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  28. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  29. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  30. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  31. 2020Boosting Contrastive Self-Supervised Learning with False Negative Cancellationcited by 119
  32. 2020Contrastive Learning for Label-Efficient Semantic Segmentationcited by 93
  33. 2020DMT: Dynamic Mutual Training for Semi-Supervised Learningcited by 77
  34. 2020Conditional Negative Sampling for Contrastive Learning of Visual Representationscited by 57
  35. 2020Structured Consistency Loss for semi-supervised semantic segmentationcited by 39
  36. 2020Improving Semantic Segmentation via Self-Trainingcited by 30
  37. 2017Mix-and-Match Tuning for Self-Supervised Semantic Segmentationcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 32; 2023: 38; 2024: 21; 2025: 9; 2026: 1.

101 papers.

Sort:

By area:

  1. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  2. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 177
  3. 2023Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentationcited by 115
  4. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  5. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  6. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  7. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 53
  8. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  9. 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50
  10. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  11. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  12. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 43
38 more
  1. 2023SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidancecited by 41
  2. 2023Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentationcited by 35
  3. 2024AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentationcited by 35
  4. 2023Semi-Supervised Semantic Segmentation via Gentle Teaching Assistantcited by 34
  5. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  6. 2022Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentationcited by 30
  7. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  8. 2023RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentationcited by 27
  9. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  10. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  11. 2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26
  12. 2023Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentationcited by 24
  13. 2023Switching Temporary Teachers for Semi-Supervised Semantic Segmentationcited by 23
  14. 2023GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentationcited by 22
  15. 2022Decoder Denoising Pretraining for Semantic Segmentationcited by 20
  16. 2022ContrastMask: Contrastive Learning to Segment Every Thingcited by 19
  17. 2022Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysiscited by 19
  18. 2022Fuzzy Positive Learning for Semi-supervised Semantic Segmentationcited by 19
  19. 2022Is Self-Supervised Learning More Robust Than Supervised Learning?cited by 17
  20. 2023A Survey on Semi-Supervised Semantic Segmentationcited by 16
  21. 2024Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentationcited by 16
  22. 2022CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentationcited by 13
  23. 2024DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentationcited by 13
  24. 2022Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentationcited by 12
  25. 2022Semi-supervised Semantic Segmentation with Mutual Knowledge Distillationcited by 12
  26. 2023JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recoverycited by 12
  27. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  28. 2024Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifiercited by 12
  29. 2024RESMatch: Referring Expression Segmentation in a Semi-Supervised Mannercited by 11
  30. 2022Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representationscited by 10
  31. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  32. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
  33. 2023Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentationcited by 8
  34. 2023Contrastive Multi-Task Dense Predictioncited by 8
  35. 2023Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentationcited by 8
  36. 2023Semi-Supervised Semantic Segmentation via Marginal Contextual Informationcited by 8
  37. 2025Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learningcited by 8
  38. 2023Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotationcited by 7

50 most cited of 101 All 101 (JSON)