mlsanityData to 7 Oct 2026

Domain-Agnostic Prior for Transfer Semantic Segmentation

arXiv 2204.02684 ↗First posted 6 Apr 2022cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. The key difficulty lies in defining a common property between the source and target domains so that the source-domain features can align with the target-domain semantics. In this paper, we present a simple and effective mechanism that regularizes cross-domain representation learning with a domain-agnostic prior (DAP) that constrains the features extracted from source and target domains to align with a domain-agnostic space. In practice, this is easily implemented as an extra loss term that requires a little extra costs. In the standard evaluation protocol of transferring synthesized data to real data, we validate the effectiveness of different types of DAP, especially that borrowed from a text embedding model that shows favorable performance beyond the state-of-the-art UDA approaches in terms of segmentation accuracy. Our research reveals that UDA benefits much from better proxies, possibly from other data modalities.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 50 of its 65 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

50 of 65 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  9. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  11. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  12. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
38 more
  1. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  2. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  3. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  4. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  5. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  6. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  7. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  8. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  9. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  10. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  11. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  12. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  13. 2019Confidence Regularized Self-Trainingcited by 418
  14. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  15. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  16. 2019Zero-Shot Semantic Segmentationcited by 245
  17. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  18. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  19. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  20. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  21. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  22. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  23. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  24. 2019Prototype Rectification for Few-Shot Learningcited by 96
  25. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  26. 2019Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detectioncited by 83
  27. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  28. 2017Open Vocabulary Scene Parsingcited by 76
  29. 2018Unsupervised Domain Adaptive Re-Identification: Theory and Practicecited by 69
  30. 2020Two-phase Pseudo Label Densification for Self-training based Domain Adaptationcited by 60
  31. 2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
  32. 2020Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentationcited by 45
  33. 2021DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentationcited by 45
  34. 2021MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentationcited by 43
  35. 2020Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignmentcited by 29
  36. 2020Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashingcited by 26
  37. 2021Dual Path Learning for Domain Adaptation of Semantic Segmentationcited by 26
  38. 2021Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptationcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 6; 2024: 5; 2025: 2.

18 papers.

Sort:

By area:

  1. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  2. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  3. 2022Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentationcited by 46
  4. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  5. 2023Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentationcited by 27
  6. 2023Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentationcited by 8
  7. 2022Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrationscited by 7
  8. 2023Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentationcited by 7
  9. 2025CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrievalcited by 6
  10. 2023Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentationcited by 5
  11. 2024AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentationcited by 5
  12. 2024Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentationcited by 5
6 more
  1. 2023Cross-modal & Cross-domain Learning for Unsupervised LiDAR Semantic Segmentationcited by 4
  2. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  3. 2022Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixingcited by 3
  4. 2024Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptationcited by 1
  5. 2025Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasetscited by 1
  6. 2024Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentationcited by 0