mlsanityData to 13 Oct 2026

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

arXiv 2010.08666 ↗First posted 16 Oct 2020cs.CV cs.LGcited by 71

Not on the map. Why?

Abstract (arXiv)

Generalizing deep neural networks to new target domains is critical to their real-world utility. In practice, it may be feasible to get some target data labeled, but to be cost-effective it is desirable to select a maximally-informative subset via active learning (AL). We study the problem of AL under a domain shift, called Active Domain Adaptation (Active DA). We demonstrate how existing AL approaches based solely on model uncertainty or diversity sampling are less effective for Active DA. We propose Clustering Uncertainty-weighted Embeddings (CLUE), a novel label acquisition strategy for Active DA that performs uncertainty-weighted clustering to identify target instances for labeling that are both uncertain under the model and diverse in feature space. CLUE consistently outperforms competing label acquisition strategies for Active DA and AL across learning settings on 6 diverse domain shifts for image classification.

Key facts. Cited by 71 papers in the map (data through 13 Oct 2026). First posted on arXiv 16 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 10; 2022: 13; 2023: 20; 2024: 12; 2025: 12; 2026: 4.

71 papers.

Sort:

By area:

  1. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 56
  2. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  3. 2023A comprehensive survey on deep active learning in medical image analysiscited by 34
  4. 2021LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentationcited by 33
  5. 2023Active learning for data streams: a surveycited by 29
  6. 2022Plug and Play Active Learning for Object Detectioncited by 28
  7. 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptationcited by 23
  8. 2023Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detectioncited by 22
  9. 2022Prior Knowledge Guided Unsupervised Domain Adaptationcited by 20
  10. 2021S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptationcited by 19
  11. 2022Learning Distinctive Margin toward Active Domain Adaptationcited by 18
  12. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
38 more
  1. 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithmcited by 18
  2. 2021Discrepancy-Based Active Learning for Domain Adaptationcited by 16
  3. 2024Active Learning for Vision-Language Modelscited by 15
  4. 2022Combating Label Distribution Shift for Active Domain Adaptationcited by 14
  5. 2023Evidential Uncertainty Quantification: A Variance-Based Perspectivecited by 14
  6. 2021Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detectioncited by 13
  7. 2023Divide and Adapt: Active Domain Adaptation via Customized Learningcited by 13
  8. 2022Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Surveycited by 12
  9. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  10. 2022Active Source Free Domain Adaptationcited by 10
  11. 2022SALAD: Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and Detectioncited by 10
  12. 2021Online Continual Adaptation with Active Self-Trainingcited by 8
  13. 2021Bayesian Active Learning for Sim-to-Real Robotic Perceptioncited by 8
  14. 2022Placing Human Animations into 3D Scenes by Learning Interaction- and Geometry-Driven Keyframescited by 8
  15. 2024Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistencecited by 8
  16. 2023Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentationcited by 7
  17. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
  18. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  19. 2021TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentationcited by 5
  20. 2022D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentationcited by 5
  21. 2023Training-Free Neural Active Learning with Initialization-Robustness Guaranteescited by 5
  22. 2024ALPBench: A Benchmark for Active Learning Pipelines on Tabular Datacited by 5
  23. 2022Local Context-Aware Active Domain Adaptationcited by 4
  24. 2025Generative Active Adaptation for Drifting and Imbalanced Network Intrusion Detectioncited by 4
  25. 2025Understanding Knowledge Transferability for Transfer Learning: A Surveycited by 4
  26. 2025Unified modality separation: A vision-language framework for unsupervised domain adaptationcited by 4
  27. 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
  28. 2022Cost-effective Framework for Gradual Domain Adaptation with Multifidelitycited by 3
  29. 2023ASPEST: Bridging the Gap Between Active Learning and Selective Predictioncited by 3
  30. 2023Spectral Transfer Guided Active Domain Adaptation For Thermal Imagerycited by 3
  31. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 3
  32. 2024Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guaranteescited by 3
  33. 2025Test-Time Adaptation with Binary Feedbackcited by 3
  34. 2025Certainty and Uncertainty Guided Active Domain Adaptationcited by 3
  35. 2023How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learningcited by 2
  36. 2024Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Datacited by 2
  37. 2024DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptationcited by 2
  38. 2022Loss-based Sequential Learning for Active Domain Adaptationcited by 1

50 most cited of 71 All 71 (JSON)