mlsanityData to 7 Oct 2026

LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation

arXiv 2108.05570 ↗First posted 12 Aug 2021cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) for semantic segmentation has been actively studied to mitigate the domain gap between label-rich source data and unlabeled target data. Despite these efforts, UDA still has a long way to go to reach the fully supervised performance. To this end, we propose a Labeling Only if Required strategy, LabOR, where we introduce a human-in-the-loop approach to adaptively give scarce labels to points that a UDA model is uncertain about. In order to find the uncertain points, we generate an inconsistency mask using the proposed adaptive pixel selector and we label these segment-based regions to achieve near supervised performance with only a small fraction (about 2.2%) ground truth points, which we call "Segment based Pixel-Labeling (SPL)". To further reduce the efforts of the human annotator, we also propose "Point-based Pixel-Labeling (PPL)", which finds the most representative points for labeling within the generated inconsistency mask. This reduces efforts from 2.2% segment label to 40 points label while minimizing performance degradation. Through extensive experimentation, we show the advantages of this new framework for domain adaptive semantic segmentation while minimizing human labor costs.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 12 Aug 2021.

Builds on

43 of 61 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  10. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  11. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  12. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
31 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. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
  6. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  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. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  10. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  11. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  12. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  13. 2017Image to Image Translation for Domain Adaptationcited by 171
  14. 2017Playing for Benchmarkscited by 169
  15. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  16. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  17. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  18. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  19. 2019Active Adversarial Domain Adaptationcited by 73
  20. 2020Detecting Human-Object Interactions with Action Co-occurrence Priorscited by 72
  21. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  22. 2020Phase Consistent Ecological Domain Adaptationcited by 62
  23. 2020Two-phase Pseudo Label Densification for Self-training based Domain Adaptationcited by 60
  24. 2020Domain Adaptive Semantic Segmentation Using Weak Labelscited by 56
  25. 2020Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentationcited by 35
  26. 2018Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Trainingcited by 31
  27. 2019Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approachcited by 30
  28. 2017Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captionercited by 21
  29. 2019Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translationcited by 20
  30. 2021MCDAL: Maximum Classifier Discrepancy for Active Learningcited by 18
  31. 2018Disjoint Multi-task Learning between Heterogeneous Human-centric Taskscited by 16

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 4; 2023: 13; 2024: 5; 2025: 7.

33 papers.

Sort:

  1. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  2. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 56
  3. 2023SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Imagescited by 35
  4. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  5. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  6. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  7. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
  8. 2024ESA: Annotation-Efficient Active Learning for Semantic Segmentationcited by 15
  9. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  10. 2022Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognitioncited by 8
  11. 2023Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentationcited by 7
  12. 2021Single-Modal Entropy based Active Learning for Visual Question Answeringcited by 6
21 more
  1. 2021TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentationcited by 5
  2. 2022D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentationcited by 5
  3. 2023MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentationcited by 5
  4. 2023Semi-Supervised Image Captioning by Adversarially Propagating Labeled Datacited by 4
  5. 2024PIG: Prompt Images Guidance for Night-Time Scene Parsingcited by 4
  6. 2023Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learningcited by 2
  7. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 2
  8. 2024SS-ADA: A Semi-Supervised Active Domain Adaptation Framework for Semantic Segmentationcited by 2
  9. 2024Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Datacited by 2
  10. 2022UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipelinecited by 1
  11. 2023ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentationcited by 1
  12. 2023Density Matters: Improved Core-set for Active Domain Adaptive Segmentationcited by 1
  13. 2024D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignmentcited by 1
  14. 2025SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentationcited by 1
  15. 2022Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shiftcited by 0
  16. 2025HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancementcited by 0
  17. 2025Deeply Dual Supervised learning for melanoma recognitioncited by 0
  18. 2025Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsamplingcited by 0
  19. 2025DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentationcited by 0
  20. 2025VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagationcited by 0
  21. 2025GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptationcited by 0