mlsanityData to 7 Oct 2026

Bootstrapping Semantic Segmentation with Regional Contrast

arXiv 2104.04465 ↗First posted 9 Apr 2021cs.CV cs.LGcited by 80

Not on the map. Why?

Abstract (arXiv)

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint. ReCo is easy to implement, being built on top of off-the-shelf segmentation networks, and consistently improves performance in both semi-supervised and supervised semantic segmentation methods, achieving smoother segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve high-quality semantic segmentation models, requiring only 5 examples of each semantic class. Code is available at https://github.com/lorenmt/reco.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

30 of 44 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  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. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  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. 2020Supervised Contrastive Learningcited by 2,803
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
18 more
  1. 2019Panoptic Feature Pyramid Networkscited by 644
  2. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  3. 2019PointRend: Image Segmentation as Renderingcited by 439
  4. 2019Confidence Regularized Self-Trainingcited by 418
  5. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  6. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  7. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  8. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  9. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  10. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  11. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  12. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  13. 2020Contrastive Learning for Label-Efficient Semantic Segmentationcited by 93
  14. 2020DMT: Dynamic Mutual Training for Semi-Supervised Learningcited by 77
  15. 2020FeatMatch: Feature-Based Augmentation for Semi-Supervised Learningcited by 57
  16. 2018Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Modelcited by 45
  17. 2018Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Trainingcited by 31
  18. 2020Improving Semantic Segmentation via Self-Trainingcited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 22; 2023: 24; 2024: 15; 2025: 10; 2026: 4.

80 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. 2023DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Modelscited by 122
  4. 2023Grounding Everything: Emerging Localization Properties in Vision-Language Transformerscited by 89
  5. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  6. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 53
  7. 2021ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenescited by 47
  8. 2022UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentationcited by 45
  9. 2023Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspectivecited by 43
  10. 2023Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentationcited by 35
  11. 2022Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labelscited by 30
  12. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
38 more
  1. 2022Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillationcited by 26
  2. 2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26
  3. 2023Switching Temporary Teachers for Semi-Supervised Semantic Segmentationcited by 23
  4. 2022Learning from Future: A Novel Self-Training Framework for Semantic Segmentationcited by 21
  5. 2023Alternate Diverse Teaching for Semi-supervised Medical Image Segmentationcited by 21
  6. 2022Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysiscited by 19
  7. 2022Contrastive Learning for Prompt-Based Few-Shot Language Learnerscited by 17
  8. 2024SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentationcited by 17
  9. 2022Semantic Segmentation with Active Semi-Supervised Learningcited by 16
  10. 2023A Survey on Semi-Supervised Semantic Segmentationcited by 16
  11. 2024Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentationcited by 16
  12. 2023LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuningcited by 15
  13. 2022Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learningcited by 14
  14. 2022Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videoscited by 12
  15. 2022Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholdingcited by 12
  16. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  17. 2021n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentationcited by 10
  18. 2022Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representationscited by 10
  19. 2021GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Referencecited by 9
  20. 2023Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentationcited by 8
  21. 2023Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentationcited by 8
  22. 2023Semi-Supervised Semantic Segmentation via Marginal Contextual Informationcited by 8
  23. 2025Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learningcited by 8
  24. 2021Multi-dataset Pretraining: A Unified Model for Semantic Segmentationcited by 7
  25. 2022Self-Supervised Image Representation Learning with Geometric Set Consistencycited by 7
  26. 2023Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentationcited by 7
  27. 2023Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotationcited by 7
  28. 2023Class-level Multiple Distributions Representation are Necessary for Semantic Segmentationcited by 5
  29. 2024S4: Self-Supervised Sensing Across the Spectrumcited by 5
  30. 2022Information-guided pixel augmentation for pixel-wise contrastive learningcited by 4
  31. 2023Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentationcited by 4
  32. 2023Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Networkcited by 4
  33. 2023GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labelscited by 4
  34. 2023Semi-supervised Semantic Segmentation Meets Masked Modeling:Fine-grained Locality Learning Matters in Consistency Regularizationcited by 4
  35. 2024CrossMatch: Enhance Semi-Supervised Medical Image Segmentation with Perturbation Strategies and Knowledge Distillationcited by 4
  36. 2024Fine-grained Background Representation for Weakly Supervised Semantic Segmentationcited by 4
  37. 2022Semantic Segmentation with Active Semi-Supervised Representation Learningcited by 3
  38. 2024PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentationcited by 3

50 most cited of 80 All 80 (JSON)