mlsanityData to 7 Oct 2026

A Comparative Survey of Deep Active Learning

arXiv 2203.13450 ↗First posted 25 Mar 2022cs.LGcited by 88

Not on the map. Why?

Abstract (arXiv)

While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data for labeling and training. Therefore, Deep Active Learning (DAL) has risen as a feasible solution for maximizing model performance under a limited labeling cost/budget in recent years. Although abundant methods of DAL have been developed and various literature reviews conducted, the performance evaluation of DAL methods under fair comparison settings is not yet available. Our work intends to fill this gap. In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods. We survey and categorize DAL-related works and construct comparative experiments across frequently used datasets and DAL algorithms. Additionally, we explore some factors (e.g., batch size, number of epochs in the training process) that influence the efficacy of DAL, which provides better references for researchers to design their DAL experiments or carry out DAL-related applications.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Builds on 42 of its 86 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

42 of 86 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2017Billion-scale similarity search with GPUscited by 2,477
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  8. 2017Deep Bayesian Active Learning with Image Datacited by 812
  9. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  10. 2020A Survey of Deep Active Learningcited by 547
  11. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  12. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
30 more
  1. 2019Learning Loss for Active Learningcited by 335
  2. 2019Variational Adversarial Active Learningcited by 284
  3. 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
  4. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 165
  5. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  6. 2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 150
  7. 2021Batch Active Learning at Scalecited by 127
  8. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  9. 2019Discriminative Active Learningcited by 97
  10. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
  11. 2019Diverse mini-batch Active Learningcited by 88
  12. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  13. 2017Deep Active Learning over the Long Tailcited by 82
  14. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  15. 2017Generative Adversarial Active Learningcited by 69
  16. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  17. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  18. 2020Scalable Active Learning for Object Detectioncited by 58
  19. 2019Bayesian Generative Active Deep Learningcited by 57
  20. 2020Reinforced active learning for image segmentationcited by 56
  21. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
  22. 2019Batch Active Learning Using Determinantal Point Processescited by 42
  23. 2021A survey of active learning algorithms for supervised remote sensing image classificationcited by 27
  24. 2019Epistemic Uncertainty Samplingcited by 24
  25. 2020Active Crowd Counting with Limited Supervisioncited by 20
  26. 2021Boosting Active Learning via Improving Test Performancecited by 19
  27. 2020On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?cited by 18
  28. 2021DeepAL: Deep Active Learning in Pythoncited by 13
  29. 2021Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processescited by 9
  30. 2021Towards General and Efficient Active Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 23; 2024: 29; 2025: 18; 2026: 9.

88 papers.

Sort:

By area:

  1. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  2. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  3. 2022A Survey of Active Learning for Natural Language Processingcited by 40
  4. 2023Continuous Learning for Android Malware Detectioncited by 33
  5. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  6. 2024Active Generalized Category Discoverycited by 31
  7. 2022A Survey on Video Action Recognition in Sports: Datasets, Methods and Applicationscited by 27
  8. 2023Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessmentcited by 25
  9. 2024What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?cited by 22
  10. 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
  11. 2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
  12. 2025From Selection to Generation: A Survey of LLM-based Active Learningcited by 18
38 more
  1. 2024ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Drivingcited by 16
  2. 2024Causal-Guided Active Learning for Debiasing Large Language Modelscited by 15
  3. 2023Black-Box Batch Active Learning for Regressioncited by 12
  4. 2023DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networkscited by 11
  5. 2024A Cross-Domain Benchmark for Active Learningcited by 11
  6. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  7. 2024All models are wrong, some are useful: Model Selection with Limited Labelscited by 8
  8. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  9. 2023On the Opportunities of Green Computing: A Surveycited by 7
  10. 2024Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitionscited by 7
  11. 2024Lidar Panoptic Segmentation in an Open Worldcited by 7
  12. 2022FAL-CUR: Fair Active Learning using Uncertainty and Representativeness on Fair Clusteringcited by 6
  13. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 6
  14. 2023ActiveLab: Active Learning with Re-Labeling by Multiple Annotatorscited by 5
  15. 2023Active Coarse-to-Fine Segmentation of Moveable Parts from Real Imagescited by 5
  16. 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samplescited by 5
  17. 2024Deep Active Learning in the Open Worldcited by 5
  18. 2022Boosting Robustness Verification of Semantic Feature Neighborhoodscited by 4
  19. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4
  20. 2023Cache & Distil: Optimising API Calls to Large Language Modelscited by 4
  21. 2025General Information Metrics for Improving AI Model Training Efficiencycited by 4
  22. 2022Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarioscited by 3
  23. 2022Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detectioncited by 3
  24. 2023HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labelingcited by 3
  25. 2023Exploring Data Redundancy in Real-world Image Classification through Data Selectioncited by 3
  26. 2024Predictive Accuracy-Based Active Learning for Medical Image Segmentationcited by 3
  27. 2024Beyond Size and Class Balance: Alpha as a New Dataset Quality Metric for Deep Learningcited by 3
  28. 2024Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimationcited by 3
  29. 2024Class Balance Matters to Active Class-Incremental Learningcited by 3
  30. 2025Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspectivecited by 3
  31. 2023Disambiguation of Company names via Deep Recurrent Networkscited by 2
  32. 2023M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Taskscited by 2
  33. 2023ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLPcited by 2
  34. 2023SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentationcited by 2
  35. 2023How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learningcited by 2
  36. 2024Direct Acquisition Optimization for Low-Budget Active Learningcited by 2
  37. 2024Scoping Review of Active Learning Strategies and their Evaluation Environments for Entity Recognition Taskscited by 2
  38. 2024DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptationcited by 2

50 most cited of 88 All 88 (JSON)