mlsanityData to 14 Oct 2026

Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation

arXiv 2306.09098 ↗First posted 15 Jun 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous approaches have attempted to reduce the gap either at the pixel or feature level, disregarding the fact that the two components interact positively. To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation. We introduce well-estimated prototypes by including category-wise cross-domain information to link the two alignments: the pixel-level alignment is achieved using the jointly trained style transfer module with the prototypical semantic consistency, while the feature-level alignment is enforced to cross-domain features with the pixel-to-prototype contrast. Our extensive experiments demonstrate that our method outperforms existing state-of-the-art methods using DeepLabV2. Our code is available at https://github.com/cxa9264/CONFETI

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 52 of its 66 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

52 of 66 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  12. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
38 more
  1. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  2. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  3. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 639
  4. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  5. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  6. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  7. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  8. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  9. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  10. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 243
  11. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  12. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  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. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  16. 2017Image to Image Translation for Domain Adaptationcited by 171
  17. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  18. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  19. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  20. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  21. 2018Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mappingcited by 113
  22. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  23. 2017One-Sided Unsupervised Domain Mappingcited by 91
  24. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  25. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  26. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  27. 2020Phase Consistent Ecological Domain Adaptationcited by 62
  28. 2017From source to target and back: symmetric bi-directional adaptive GANcited by 53
  29. 2022Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentationcited by 47
  30. 2022Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentationcited by 40
  31. 2021Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularizationcited by 36
  32. 2019Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptationcited by 32
  33. 2020Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignmentcited by 29
  34. 2023Semantic Image Segmentation: Two Decades of Researchcited by 27
  35. 2022DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentationcited by 23
  36. 2021Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentationcited by 19
  37. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  38. 2019Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentationcited by 8

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 6.

11 papers.

  1. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 28
  2. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  3. 2025SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentationcited by 4
  4. 2024Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Taskscited by 3
  5. 2025DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentationcited by 3
  6. 2024Unsupervised Domain Adaptive Lane Detection via Contextual Contrast and Aggregationcited by 1
  7. 2024Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrastcited by 0
  8. 2025Dictionary-based Framework for Interpretable and Consistent Object Parsingcited by 0
  9. 2025Masked Representation Modeling for Domain-Adaptive Segmentationcited by 0
  10. 2025Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopycited by 0
  11. 2025OMUDA: Omni-level Masking for Unsupervised Domain Adaptation in Semantic Segmentationcited by 0