mlsanityData to 7 Oct 2026

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

arXiv 2103.02584 ↗First posted 3 Mar 2021cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Panoptic segmentation unifies semantic segmentation and instance segmentation which has been attracting increasing attention in recent years. However, most existing research was conducted under a supervised learning setup whereas unsupervised domain adaptive panoptic segmentation which is critical in different tasks and applications is largely neglected. We design a domain adaptive panoptic segmentation network that exploits inter-style consistency and inter-task regularization for optimal domain adaptive panoptic segmentation. The inter-style consistency leverages geometric invariance across the same image of the different styles which fabricates certain self-supervisions to guide the network to learn domain-invariant features. The inter-task regularization exploits the complementary nature of instance segmentation and semantic segmentation and uses it as a constraint for better feature alignment across domains. Extensive experiments over multiple domain adaptive panoptic segmentation tasks (e.g., synthetic-to-real and real-to-real) show that our proposed network achieves superior segmentation performance as compared with the state-of-the-art.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 58 of its 81 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

58 of 81 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  6. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2018Panoptic Segmentationcited by 796
  10. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  11. 2019Panoptic Feature Pyramid Networkscited by 644
  12. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
38 more
  1. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  2. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  3. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  4. 2019Confidence Regularized Self-Trainingcited by 418
  5. 2019Panoptic-DeepLabcited by 362
  6. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  7. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  8. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  9. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  10. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  11. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  12. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  13. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  14. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  15. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  16. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  17. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 136
  18. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  19. 2020Exploring Categorical Regularization for Domain Adaptive Object Detectioncited by 130
  20. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  21. 2019Seamless Scene Segmentationcited by 112
  22. 2017Adversarial Dropout Regularizationcited by 106
  23. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  24. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  25. 2018Attention-guided Unified Network for Panoptic Segmentationcited by 71
  26. 2020Contextual-Relation Consistent Domain Adaptation for Semantic Segmentationcited by 70
  27. 2019Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptationcited by 62
  28. 2020Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentationcited by 62
  29. 2020Two-phase Pseudo Label Densification for Self-training based Domain Adaptationcited by 60
  30. 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59
  31. 2018Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detectioncited by 57
  32. 2020Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNNcited by 55
  33. 2019An End-to-End Network for Panoptic Segmentationcited by 46
  34. 2018Effective Use of Synthetic Data for Urban Scene Semantic Segmentationcited by 41
  35. 2020Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentationcited by 41
  36. 2017Adversarial Dropout for Supervised and Semi-supervised Learningcited by 38
  37. 2020Unifying Training and Inference for Panoptic Segmentationcited by 37
  38. 2020iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detectioncited by 35

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 9; 2023: 6; 2024: 10; 2025: 1; 2026: 2.

41 papers.

Sort:

By area:

  1. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  2. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  3. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  4. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  5. 2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48
  6. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  7. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  8. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  9. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  10. 2021DA-DETR: Domain Adaptive Detection Transformer with Information Fusioncited by 24
  11. 2021Domain Adaptive Video Segmentation via Temporal Consistency Regularizationcited by 21
  12. 2021Panoptic Segmentation: A Reviewcited by 18
29 more
  1. 2023CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentationcited by 18
  2. 2023EDAPS: Enhanced Domain-Adaptive Panoptic Segmentationcited by 17
  3. 2021MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentationcited by 16
  4. 2022Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglementcited by 15
  5. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  6. 2024Learning to Prompt Segment Anything Modelscited by 13
  7. 2022Domain Adaptive Video Segmentation via Temporal Pseudo Supervisioncited by 11
  8. 2024Open-Vocabulary Object Detection via Language Hierarchycited by 10
  9. 2023Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignmentcited by 9
  10. 2022UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibrationcited by 8
  11. 2021Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classificationcited by 6
  12. 2024EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understandingcited by 6
  13. 2021Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignmentcited by 4
  14. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  15. 2024MC-PanDA: Mask Confidence for Panoptic Domain Adaptationcited by 4
  16. 2024Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Taskscited by 3
  17. 2025Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentationcited by 3
  18. 2021CAR -- Cityscapes Attributes Recognition A Multi-category Attributes Dataset for Autonomous Vehiclescited by 2
  19. 2022Domain Adaptive Scene Text Detection via Subcategorizationcited by 2
  20. 2024Domain Adaptation for Large-Vocabulary Object Detectorscited by 2
  21. 2024Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detectioncited by 2
  22. 2022Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentationcited by 1
  23. 2023Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptationcited by 1
  24. 2024UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentationcited by 1
  25. 2024Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Taskscited by 1
  26. 2022IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labelscited by 0
  27. 2022A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentationcited by 0
  28. 2026Time2General: Learning Spatiotemporal Invariant Representations for Domain-Generalization Video Semantic Segmentationcited by 0
  29. 2026MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentationcited by 0