mlsanityData to 7 Oct 2026

Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning

arXiv 2303.01906 ↗First posted 3 Mar 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain generalization methods learn domain invariant features by suppressing domain sensitive features. Different from them, we propose a Domain Projection and Contrastive Learning (DPCL) approach for generalized semantic segmentation, which includes two modules: Self-supervised Source Domain Projection (SSDP) and Multi-level Contrastive Learning (MLCL). SSDP aims to reduce domain gap by projecting data to the source domain, while MLCL is a learning scheme to learn discriminative and generalizable features on the projected data. During test time, we first project the target data by SSDP to mitigate domain shift, then generate the segmentation results by the learned segmentation network based on MLCL. At test time, we can update the projected data by minimizing our proposed pixel-to-pixel contrastive loss to obtain better results. Extensive experiments for semantic segmentation demonstrate the favorable generalization capability of our method on benchmark datasets.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

43 of 54 references.

References · 43

  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. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  10. 2020Supervised Contrastive Learningcited by 2,803
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  12. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
31 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  2. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  3. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  4. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  5. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  6. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  7. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  8. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  9. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  10. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  11. 2022Contrastive Test-Time Adaptationcited by 258
  12. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
  13. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  14. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  15. 2015ParseNet: Looking Wider to See Bettercited by 176
  16. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  17. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  18. 2019Switchable Whitening for Deep Representation Learningcited by 105
  19. 2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
  20. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  21. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  22. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  23. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  24. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 56
  25. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 48
  26. 2022Compound Domain Generalization via Meta-Knowledge Encodingcited by 40
  27. 2021Contrastive Syn-to-Real Generalizationcited by 32
  28. 2018Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Trainingcited by 31
  29. 2022Learning to Generalize across Domains on Single Test Samplescited by 24
  30. 2022Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentationcited by 7
  31. 2021Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 4; 2026: 1.

11 papers.

  1. 2024Frequency-aware Feature Fusion for Dense Image Predictioncited by 48
  2. 2023A Simple Recipe for Language-guided Domain Generalized Segmentationcited by 27
  3. 2024SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learningcited by 22
  4. 2024Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learningcited by 17
  5. 2024Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentationcited by 7
  6. 2024StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalizationcited by 5
  7. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  8. 2025Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentationcited by 3
  9. 2025Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Modelscited by 0
  10. 2025Domain Generalization for Semantic Segmentation: A Surveycited by 0
  11. 2026LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentationcited by 0