mlsanityData to 14 Oct 2026

Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation

arXiv 2204.13314 ↗First posted 28 Apr 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and pixel-level contrastive regularization has memory and computational cost with O(pixelnum2). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC2L) for semi-supervised semantic segmentation. Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to accomplish region-level contrastive property. Furthermore, Region Class Consistency (RCC) loss and Semantic Mask Consistency (SMC) loss are proposed for achieving region-level consistency. Based on the proposed region-level contrastive and consistency regularization, we develop a region-level contrastive and consistency learning framework (RC2L) for semi-supervised semantic segmentation, and evaluate our RC2L on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes), outperforming the state-of-the-art.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

24 of 30 references.

References · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  10. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  11. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  12. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
12 more
  1. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  2. 2020Rethinking Pre-training and Self-trainingcited by 352
  3. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  4. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  5. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  6. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  7. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  8. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  9. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  10. 2018CGNet: A Light-weight Context Guided Network for Semantic Segmentationcited by 94
  11. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  12. 2020GINet: Graph Interaction Network for Scene Parsingcited by 13

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 4; 2025: 3.

12 papers.

  1. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  2. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 54
  3. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 44
  4. 2024Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Surveycited by 12
  5. 2025Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learningcited by 8
  6. 2023CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentationcited by 4
  7. 2023Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentationcited by 2
  8. 2024CktGen: Automated Analog Circuit Design with Generative Artificial Intelligencecited by 2
  9. 2025IGL-DT: Iterative Global-Local Feature Learning with Dual-Teacher Semantic Segmentation Framework under Limited Annotation Schemecited by 2
  10. 2024IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relationcited by 1
  11. 2025ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generationcited by 1
  12. 2023Semi-supervised Semantic Segmentation via Boosting Uncertainty on Unlabeled Datacited by 0