mlsanityData to 7 Oct 2026

Class-Incremental Domain Adaptation

arXiv 2008.01389 ↗First posted 4 Aug 2020cs.LG cs.CV stat.MLcited by 36

Not on the map. Why?

Abstract (arXiv)

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 8; 2023: 10; 2024: 4; 2025: 1; 2026: 1.

36 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2021Generalized Source-free Domain Adaptationcited by 175
  3. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  4. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  5. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  6. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  7. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  8. 2021Your Classifier can Secretly Suffice Multi-Source Domain Adaptationcited by 42
  9. 2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
  10. 2024Online DPO: Online Direct Preference Optimization with Fast-Slow Chasingcited by 38
  11. 2022Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptationcited by 33
  12. 2023POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelscited by 29
24 more
  1. 2022General Incremental Learning with Domain-aware Categorical Representationscited by 26
  2. 2021Multi-Domain Incremental Learning for Semantic Segmentationcited by 25
  3. 2022On Generalizing Beyond Domains in Cross-Domain Continual Learningcited by 25
  4. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  5. 2021The First Vision For Vitals (V4V) Challenge for Non-Contact Video-Based Physiological Estimationcited by 19
  6. 2021Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generationcited by 18
  7. 2024Training-Free Model Merging for Multi-target Domain Adaptationcited by 15
  8. 2023Gradient-Semantic Compensation for Incremental Semantic Segmentationcited by 10
  9. 2024Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptationcited by 10
  10. 2021Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentationcited by 9
  11. 2023Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRIcited by 9
  12. 2021Semi-Supervised Visual Representation Learning for Fashion Compatibilitycited by 8
  13. 2024Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptationcited by 8
  14. 2023Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillationcited by 6
  15. 2021TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentationcited by 5
  16. 2023Online Continual Learning via Logit Adjusted Softmaxcited by 5
  17. 2023Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detectioncited by 3
  18. 2025Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Taskscited by 2
  19. 2021On the Challenges of Open World Recognitionunder Shifting Visual Domainscited by 1
  20. 2022Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosiscited by 1
  21. 2023Adversarial Learning Networks: Source-free Unsupervised Domain Incremental Learningcited by 1
  22. 2023Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptationcited by 1
  23. 2023TIDo: Source-free Task Incremental Learning in Non-stationary Environmentscited by 0
  24. 2026Few-shot Class-Incremental Learning via Generative Co-Memory Regularizationcited by 0