mlsanityData to 14 Oct 2026

WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels

arXiv 2210.02088 ↗First posted 5 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation (UDA) for semantic segmentation addresses the cross-domain problem with fine source domain labels. However, the acquisition of semantic labels has always been a difficult step, many scenarios only have weak labels (e.g. bounding boxes). For scenarios where weak supervision and cross-domain problems coexist, this paper defines a new task: unsupervised domain adaptation based on weak source domain labels (WUDA). To explore solutions for this task, this paper proposes two intuitive frameworks: 1) Perform weakly supervised semantic segmentation in the source domain, and then implement unsupervised domain adaptation; 2) Train an object detection model using source domain data, then detect objects in the target domain and implement weakly supervised semantic segmentation. We observe that the two frameworks behave differently when the datasets change. Therefore, we construct dataset pairs with a wide range of domain shifts and conduct extended experiments to analyze the impact of different domain shifts on the two frameworks. In addition, to measure domain shift, we apply the metric representation shift to urban landscape image segmentation for the first time. The source code and constructed datasets are available at urlhttps://github.com/bupt-ai-cz/WUDA.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 54 of its 74 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

54 of 74 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  8. 2015Fast R-CNNcited by 2,933
  9. 2018YOLOv3: An Incremental Improvementcited by 2,659
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  12. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
38 more
  1. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  3. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  4. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  5. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  6. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  7. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  8. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  9. 2019Confidence Regularized Self-Trainingcited by 419
  10. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 331
  11. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 300
  12. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 298
  13. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  14. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  15. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 227
  16. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  17. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  18. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  19. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  20. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  21. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  22. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  23. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  24. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  25. 2018On Regularized Losses for Weakly-supervised CNN Segmentationcited by 121
  26. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  27. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
  28. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  29. 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
  30. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 98
  31. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  32. 2019Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentationcited by 74
  33. 2020Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentationcited by 62
  34. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  35. 2019An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentationcited by 48
  36. 2021Pseudo-mask Matters in Weakly-supervised Semantic Segmentationcited by 48
  37. 2022Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentationcited by 47
  38. 2021MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentationcited by 43

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.