mlsanityData to 7 Oct 2026

Unsupervised Model Adaptation for Continual Semantic Segmentation

arXiv 2009.12518 ↗First posted 26 Sep 2020cs.LG cs.CV stat.MLcited by 42

Not on the map. Why?

Abstract (arXiv)

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain adaptation (UDA) literature, but existing UDA algorithms require access to both the source domain labeled data and the target domain unlabeled data for training a domain agnostic semantic segmentation model. Relaxing this constraint enables a user to adapt pretrained models to generalize in a target domain, without requiring access to source data. To this end, we learn a prototypical distribution for the source domain in an intermediate embedding space. This distribution encodes the abstract knowledge that is learned from the source domain. We then use this distribution for aligning the target domain distribution with the source domain distribution in the embedding space. We provide theoretical analysis and explain conditions under which our algorithm is effective. Experiments on benchmark adaptation task demonstrate our method achieves competitive performance even compared with joint UDA approaches.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 10; 2023: 12; 2024: 11; 2025: 2.

42 papers.

Sort:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  5. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
  6. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  7. 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
  8. 2024Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentationcited by 34
  9. 2021Detection and Continual Learning of Novel Face Presentation Attackscited by 33
  10. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  11. 2024360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypescited by 28
  12. 2022RBC: Rectifying the Biased Context in Continual Semantic Segmentationcited by 27
30 more
  1. 2023Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectivescited by 24
  2. 2024EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 23
  3. 2022CAFA: Class-Aware Feature Alignment for Test-Time Adaptationcited by 21
  4. 2022Continual Learning for Class- and Domain-Incremental Semantic Segmentationcited by 17
  5. 2021Cognitively Inspired Learning of Incremental Drifting Conceptscited by 16
  6. 2022Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditionscited by 16
  7. 2023Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioningcited by 14
  8. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  9. 2022Unsupervised Model Adaptation for Source-free Segmentation of Medical Imagescited by 13
  10. 2021Domain Adaptation for the Segmentation of Confidential Medical Imagescited by 12
  11. 2021Secure Domain Adaptation with Multiple Sourcescited by 12
  12. 2022Continual BatchNorm Adaptation (CBNA) for Semantic Segmentationcited by 12
  13. 2023Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentationcited by 10
  14. 2023Generative appearance replay for continual unsupervised domain adaptationcited by 8
  15. 2024Dynamic Transformer Architecture for Continual Learning of Multimodal Taskscited by 8
  16. 2025Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentationcited by 7
  17. 2021Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separationcited by 4
  18. 2022Union-set Multi-source Model Adaptation for Semantic Segmentationcited by 3
  19. 2023Preserving Fairness in AI under Domain Shiftcited by 3
  20. 2022Increasing Model Generalizability for Unsupervised Domain Adaptationcited by 1
  21. 2023Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenationcited by 1
  22. 2024Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replaycited by 1
  23. 2024EventDance++: Language-guided Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 1
  24. 2024Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Imagescited by 1
  25. 2025Ranking-aware Continual Learning for LiDAR Place Recognitioncited by 1
  26. 2023Robust Internal Representations for Domain Generalizationcited by 0
  27. 2024Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representationscited by 0
  28. 2024Relating Events and Frames Based on Self-Supervised Learning and Uncorrelated Conditioning for Unsupervised Domain Adaptationcited by 0
  29. 2024Unsupervised Federated Domain Adaptation for Segmentation of MRI Imagescited by 0
  30. 2024Unsupervised Domain Adaptation Using Compact Internal Representationscited by 0