mlsanityData to 7 Oct 2026

Unsupervised Contrastive Domain Adaptation for Semantic Segmentation

arXiv 2204.08399 ↗First posted 18 Apr 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and cross-domain contrastive pairs to learn discriminative features that align across domains. Based on the resulting well-aligned feature representations we introduce a label expansion approach that is able to discover samples from hard classes during the adaptation process to further boost performance. The proposed approach consistently outperforms state-of-the-art methods for domain adaptation. It achieves 60.2% mIoU on the Cityscapes dataset when training on the synthetic GTA5 dataset together with unlabeled Cityscapes images.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 61 of its 70 references that are in the map. First posted on arXiv 18 Apr 2022.

Builds on

61 of 70 references.

References · 61

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  10. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  12. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
38 more
  1. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  2. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  3. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  4. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  5. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  6. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  7. 2020Rethinking Pre-training and Self-trainingcited by 352
  8. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  9. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  10. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  11. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  12. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  13. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  14. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  15. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  16. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  17. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  18. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  19. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  20. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  21. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  22. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  23. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  24. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  25. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  26. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  27. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  28. 2019All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentationcited by 104
  29. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  30. 2021Region Similarity Representation Learningcited by 96
  31. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  32. 2020Contrastive Learning for Label-Efficient Semantic Segmentationcited by 93
  33. 2020Self-Supervised Visual Representation Learning from Hierarchical Groupingcited by 63
  34. 2020Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentationcited by 62
  35. 2020Phase Consistent Ecological Domain Adaptationcited by 62
  36. 2020Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentationcited by 41
  37. 2020Context-Aware Domain Adaptation in Semantic Segmentationcited by 36
  38. 2021Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularizationcited by 36

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5.

6 papers.

  1. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  2. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 27
  3. 2022DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentationcited by 22
  4. 2023Augmentation-based Domain Generalization for Semantic Segmentationcited by 10
  5. 2023MSCDA: Multi-level Semantic-guided Contrast Improves Unsupervised Domain Adaptation for Breast MRI Segmentation in Small Datasetscited by 5
  6. 2023Relating tSNE and UMAP to Classical Dimensionality Reductioncited by 3