mlsanityData to 14 Oct 2026

Deep Bayesian Active Learning with Image Data

arXiv 1703.02910 ↗First posted 8 Mar 2017cs.LG cs.CV stat.MLcited by 819

Not on the map. Why?

Abstract (arXiv)

Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine recent advances in Bayesian deep learning into the active learning framework in a practical way. We develop an active learning framework for high dimensional data, a task which has been extremely challenging so far, with very sparse existing literature. Taking advantage of specialised models such as Bayesian convolutional neural networks, we demonstrate our active learning techniques with image data, obtaining a significant improvement on existing active learning approaches. We demonstrate this on both the MNIST dataset, as well as for skin cancer diagnosis from lesion images (ISIC2016 task).

Key facts. Cited by 819 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 1; 2021: 141; 2022: 174; 2023: 151; 2024: 154; 2025: 102; 2026: 94.

819 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  2. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  3. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  4. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  5. 2021Active Learning by Acquiring Contrastive Examplescited by 156
  6. 2022AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuningcited by 137
  7. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  8. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  9. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
  10. 2023Modern Bayesian Experimental Designcited by 125
  11. 2021Epistemic Neural Networkscited by 120
  12. 2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 120
38 more
  1. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  2. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 104
  3. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  4. 2022A Comparative Survey of Deep Active Learningcited by 89
  5. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  6. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  7. 2023LLMaAA: Making Large Language Models as Active Annotatorscited by 79
  8. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  9. 2021Multiple instance active learning for object detectioncited by 77
  10. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 75
  11. 2022Active Learning Through a Covering Lenscited by 66
  12. 2021Understanding Softmax Confidence and Uncertaintycited by 63
  13. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  14. 2022Active Learning by Feature Mixingcited by 63
  15. 2023Large-scale Dataset Pruning with Dynamic Uncertaintycited by 63
  16. 2025QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?cited by 63
  17. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  18. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  19. 2023Prediction-Oriented Bayesian Active Learningcited by 62
  20. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62
  21. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 61
  22. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  23. 2024Active Preference Learning for Large Language Modelscited by 58
  24. 2022BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotationcited by 54
  25. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 54
  26. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 54
  27. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  28. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  29. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  30. 2023AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weekscited by 52
  31. 2021Learning to Map for Active Semantic Goal Navigationcited by 50
  32. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  33. 2024Active Statistical Inferencecited by 50
  34. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 49
  35. 2021SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistencycited by 48
  36. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  37. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  38. 2022Optimizing Sequential Experimental Design with Deep Reinforcement Learningcited by 46

50 most cited of 819 All 819 (JSON)