mlsanityData to 7 Oct 2026

Parting with Illusions about Deep Active Learning

arXiv 1912.05361 ↗First posted 11 Dec 2019cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tasks. However, the conventional evaluation scheme used for deep active learning is below par. Current methods disregard some apparent parallel work in the closely related fields. Active learning methods are quite sensitive w.r.t. changes in the training procedure like data augmentation. They improve by a large-margin when integrated with semi-supervised learning, but barely perform better than the random baseline. We re-implement various latest active learning approaches for image classification and evaluate them under more realistic settings. We further validate our findings for semantic segmentation. Based on our observations, we realistically assess the current state of the field and propose a more suitable evaluation protocol.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 15; 2024: 8; 2025: 3; 2026: 4.

38 papers.

Sort:

  1. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  2. 2022Active Learning Through a Covering Lenscited by 62
  3. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  4. 2023Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessmentcited by 25
  5. 2024ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentationcited by 25
  6. 2024A Practitioner's Guide to Continual Multimodal Pretrainingcited by 22
  7. 2023Model Extraction Attacks Revisitedcited by 21
  8. 2023Active learning for medical image segmentation with stochastic batchescited by 20
  9. 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
  10. 2021Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasetscited by 17
  11. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
  12. 2023Uncertainty Estimation for Molecules: Desiderata and Methodscited by 11
26 more
  1. 2023Best Practices in Active Learning for Semantic Segmentationcited by 10
  2. 2024Making Better Use of Unlabelled Data in Bayesian Active Learningcited by 10
  3. 2023COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentationcited by 9
  4. 2022An Empirical Study on the Efficacy of Deep Active Learning for Image Classificationcited by 6
  5. 2024Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Trainingcited by 6
  6. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  7. 2022Active Self-Semi-Supervised Learning for Few Labeled Samplescited by 4
  8. 2021Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Trainingcited by 3
  9. 2023NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coveragecited by 3
  10. 2021Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealingcited by 2
  11. 2023Training Ensembles with Inliers and Outliers for Semi-supervised Active Learningcited by 2
  12. 2023How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learningcited by 2
  13. 2024Direct Acquisition Optimization for Low-Budget Active Learningcited by 2
  14. 2024SUPClust: Active Learning at the Boundariescited by 2
  15. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 2
  16. 2023IAdet: Simplest human-in-the-loop object detectioncited by 1
  17. 2023Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentationcited by 1
  18. 2026Finally Outshining the Random Baseline: A Simple and Effective Solution for Active Learning in 3D Biomedical Imagingcited by 1
  19. 2023Active Vision Reinforcement Learning under Limited Visual Observabilitycited by 0
  20. 2023Mining of Single-Class by Active Learning for Semantic Segmentationcited by 0
  21. 2024Key Patch Proposer: Key Patches Contain Rich Informationcited by 0
  22. 2025Efficient Data Selection for Training Genomic Perturbation Modelscited by 0
  23. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0
  24. 2026Not All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifierscited by 0
  25. 2026One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learningcited by 0
  26. 2026Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inferencecited by 0