mlsanityData to 7 Oct 2026

Deep Active Learning for Computer Vision: Past and Future

arXiv 2211.14819 ↗First posted 27 Nov 2022cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are composed of a large number of parameters and data hungry, in application. Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. In this paper, we present a review of active learning through deep active learning approaches from the following perspectives: 1) technical advancements in active learning, 2) applications of active learning in computer vision, 3) industrial systems leveraging or with potential to leverage active learning for data iteration, 4) current limitations and future research directions. We expect this paper to clarify the significance of active learning in a modern AI model manufacturing process and to bring additional research attention to active learning. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies by boosting model production at scale.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 76 of its 126 references that are in the map. First posted on arXiv 27 Nov 2022.

Builds on

76 of 126 references.

References · 76

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  8. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  9. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  10. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  11. 2017Deep Bayesian Active Learning with Image Datacited by 812
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
38 more
  1. 2020A Survey of Deep Active Learningcited by 547
  2. 2017Progressive Neural Architecture Searchcited by 483
  3. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  4. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  5. 2019Learning Loss for Active Learningcited by 335
  6. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  7. 2019Variational Adversarial Active Learningcited by 284
  8. 2018Meta-Learning: A Surveycited by 254
  9. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 165
  10. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  11. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  12. 2020Contextual Diversity for Active Learningcited by 139
  13. 2021Batch Active Learning at Scalecited by 127
  14. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  15. 2021MST: Masked Self-Supervised Transformer for Visual Representationcited by 114
  16. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  17. 2019Discriminative Active Learningcited by 97
  18. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 95
  19. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
  20. 2019Diverse mini-batch Active Learningcited by 88
  21. 2022A Comparative Survey of Deep Active Learningcited by 88
  22. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  23. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  24. 2017Deep Active Learning over the Long Tailcited by 82
  25. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  26. 2021Multiple instance active learning for object detectioncited by 77
  27. 2017Generative Adversarial Active Learningcited by 69
  28. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  29. 2019Active Learning for Deep Detection Neural Networkscited by 62
  30. 2020State-Relabeling Adversarial Active Learningcited by 60
  31. 2019Bayesian Generative Active Deep Learningcited by 57
  32. 2020Reinforced active learning for image segmentationcited by 56
  33. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  34. 2018Active Learning for Deep Object Detectioncited by 49
  35. 2018Localization-Aware Active Learning for Object Detectioncited by 48
  36. 2018CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentationcited by 47
  37. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  38. 2019Batch Active Learning Using Determinantal Point Processescited by 42

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 4; 2025: 2.

7 papers.

  1. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  2. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  3. 2024Improving Interpretability of Deep Active Learning for Flood Inundation Mapping Through Class Ambiguity Indices Using Multi-spectral Satellite Imagerycited by 6
  4. 2024Diverse Feature Learning by Self-distillation and Resetcited by 2
  5. 2024MelissaDL x Breed: Towards Data-Efficient On-line Supervised Training of Multi-parametric Surrogates with Active Learningcited by 1
  6. 2025Dependency-aware Maximum Likelihood Estimation for Active Learningcited by 0
  7. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0