mlsanityData to 7 Oct 2026

Deep Active Learning: Unified and Principled Method for Query and Training

arXiv 1911.09162 ↗First posted 20 Nov 2019cs.LG stat.MLcited by 92

Not on the map. Why?

Abstract (arXiv)

In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights from the intuition of modeling the interactive procedure in active learning as distribution matching, by adopting the Wasserstein distance. As a consequence, we derived a new training loss from the theoretical analysis, which is decomposed into optimizing deep neural network parameters and batch query selection through alternative optimization. In addition, the loss for training a deep neural network is naturally formulated as a min-max optimization problem through leveraging the unlabeled data information. Moreover, the proposed principles also indicate an explicit uncertainty-diversity trade-off in the query batch selection. Finally, we evaluate our proposed method on different benchmarks, consistently showing better empirical performances and a better time-efficient query strategy compared to the baselines.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 21; 2023: 26; 2024: 15; 2025: 6; 2026: 6.

92 papers.

Sort:

  1. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  2. 2021Batch Active Learning at Scalecited by 127
  3. 2022A Comparative Survey of Deep Active Learningcited by 88
  4. 2022Active Learning Through a Covering Lenscited by 62
  5. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  6. 2021Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approachcited by 34
  7. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  8. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  9. 2022A Lagrangian Duality Approach to Active Learningcited by 24
  10. 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptationcited by 23
  11. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  12. 2021Discrepancy-Based Active Learning for Domain Adaptationcited by 16
38 more
  1. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
  2. 2021A Simple Baseline for Low-Budget Active Learningcited by 15
  3. 2022Fast Rates in Pool-Based Batch Active Learningcited by 15
  4. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  5. 2023Evidential Uncertainty Quantification: A Variance-Based Perspectivecited by 14
  6. 2022TiDAL: Learning Training Dynamics for Active Learningcited by 11
  7. 2023DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networkscited by 11
  8. 2024Uncertainty for Active Learning on Graphscited by 11
  9. 2023Best Practices in Active Learning for Semantic Segmentationcited by 10
  10. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  11. 2024Making Better Use of Unlabelled Data in Bayesian Active Learningcited by 10
  12. 2021WOOD: Wasserstein-based Out-of-Distribution Detectioncited by 9
  13. 2023Towards Balanced Active Learning for Multimodal Classificationcited by 9
  14. 2023A Weighted K-Center Algorithm for Data Subset Selectioncited by 9
  15. 2023Accelerating Batch Active Learning Using Continual Learning Techniquescited by 8
  16. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  17. 2021Multi-Domain Active Learning: Literature Review and Comparative Studycited by 6
  18. 2022An Empirical Study on the Efficacy of Deep Active Learning for Image Classificationcited by 6
  19. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  20. 2021Less is more: Selecting informative and diverse subsets with balancing constraintscited by 5
  21. 2021Mitigating Sampling Bias and Improving Robustness in Active Learningcited by 5
  22. 2022One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learningcited by 5
  23. 2023Deep Active Learning in the Presence of Label Noise: A Surveycited by 5
  24. 2023Training-Free Neural Active Learning with Initialization-Robustness Guaranteescited by 5
  25. 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samplescited by 5
  26. 2021A Survey on Active Deep Learning: From Model-driven to Data-drivencited by 4
  27. 2021Partial Wasserstein Coveringcited by 4
  28. 2022Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learningcited by 4
  29. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4
  30. 2024Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Modelscited by 4
  31. 2024Feasibility Study on Active Learning of Smart Surrogates for Scientific Simulationscited by 4
  32. 2021Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Trainingcited by 3
  33. 2022Deep reinforced active learning for multi-class image classificationcited by 3
  34. 2022Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarioscited by 3
  35. 2022Margin-based sampling in high dimensions: When being active is less efficient than staying passivecited by 3
  36. 2023NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coveragecited by 3
  37. 2023ActiveDC: Distribution Calibration for Active Finetuningcited by 3
  38. 2024User-Side Realizationcited by 3

50 most cited of 92 All 92 (JSON)