mlsanityData to 7 Oct 2026

Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation

arXiv 2208.08437 ↗First posted 17 Aug 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Semi-supervised semantic segmentation needs rich and robust supervision on unlabeled data. Consistency learning enforces the same pixel to have similar features in different augmented views, which is a robust signal but neglects relationships with other pixels. In comparison, contrastive learning considers rich pairwise relationships, but it can be a conundrum to assign binary positive-negative supervision signals for pixel pairs. In this paper, we take the best of both worlds and propose multi-view correlation consistency (MVCC) learning: it considers rich pairwise relationships in self-correlation matrices and matches them across views to provide robust supervision. Together with this correlation consistency loss, we propose a view-coherent data augmentation strategy that guarantees pixel-pixel correspondence between different views. In a series of semi-supervised settings on two datasets, we report competitive accuracy compared with the state-of-the-art methods. Notably, on Cityscapes, we achieve 76.8% mIoU with 1/8 labeled data, just 0.6% shy from the fully supervised oracle.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 53 references that are in the map. First posted on arXiv 17 Aug 2022.

Builds on

45 of 53 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  12. 2015Spatial Transformer Networkscited by 1,423
33 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  4. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  6. 2019When Does Label Smoothing Help?cited by 985
  7. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  8. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  9. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  10. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  11. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  12. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  13. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  14. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  15. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  16. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  17. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  18. 2020Does label smoothing mitigate label noise?cited by 204
  19. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  20. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  21. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  22. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  23. 2021Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentationcited by 113
  24. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  25. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  26. 2021Semi-Supervised Semantic Segmentation via Adaptive Equalization Learningcited by 101
  27. 2020Contrastive Learning for Label-Efficient Semantic Segmentationcited by 93
  28. 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
  29. 2021A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentationcited by 79
  30. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  31. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  32. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  33. 2020Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustnesscited by 6

Built on by

Not cited yet.