mlsanityData to 14 Oct 2026

Active Learning Through a Covering Lens

arXiv 2205.11320 ↗First posted 23 May 2022cs.LGcited by 66

Not on the map. Why?

Abstract (arXiv)

Deep active learning aims to reduce the annotation cost for the training of deep models, which is notoriously data-hungry. Until recently, deep active learning methods were ineffectual in the low-budget regime, where only a small number of examples are annotated. The situation has been alleviated by recent advances in representation and self-supervised learning, which impart the geometry of the data representation with rich information about the points. Taking advantage of this progress, we study the problem of subset selection for annotation through a "covering" lens, proposing ProbCover - a new active learning algorithm for the low budget regime, which seeks to maximize Probability Coverage. We then describe a dual way to view the proposed formulation, from which one can derive strategies suitable for the high budget regime of active learning, related to existing methods like Coreset. We conclude with extensive experiments, evaluating ProbCover in the low-budget regime. We show that our principled active learning strategy improves the state-of-the-art in the low-budget regime in several image recognition benchmarks. This method is especially beneficial in the semi-supervised setting, allowing state-of-the-art semi-supervised methods to match the performance of fully supervised methods, while using much fewer labels nonetheless. Code is available at https://github.com/avihu111/TypiClust.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). Builds on 32 of its 61 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

32 of 61 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  8. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  9. 2017Deep Bayesian Active Learning with Image Datacited by 819
  10. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  11. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  12. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
20 more
  1. 2020SCAN: Learning to Classify Images without Labelscited by 352
  2. 2019Learning Loss for Active Learningcited by 336
  3. 2019Variational Adversarial Active Learningcited by 284
  4. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  5. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  6. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  7. 2019Discriminative Active Learningcited by 98
  8. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 93
  9. 2019Diverse mini-batch Active Learningcited by 89
  10. 2017Deep Active Learning over the Long Tailcited by 84
  11. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 54
  12. 2021Reducing Label Effort: Self-Supervised meets Active Learningcited by 42
  13. 2019Rethinking deep active learning: Using unlabeled data at model trainingcited by 39
  14. 2019Parting with Illusions about Deep Active Learningcited by 38
  15. 2021Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approachcited by 34
  16. 2018Addressing the Item Cold-start Problem by Attribute-driven Active Learningcited by 33
  17. 2020On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?cited by 18
  18. 2020On Initial Pools for Deep Active Learningcited by 18
  19. 2021A Simple Baseline for Low-Budget Active Learningcited by 15
  20. 2020Deep Active Learning with Augmentation-based Consistency Estimationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 19; 2025: 14; 2026: 20.

66 papers.

Sort:

By area:

  1. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 54
  2. 2023A comprehensive survey on deep active learning in medical image analysiscited by 35
  3. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  4. 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
  5. 2023Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networkscited by 18
  6. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 17
  7. 2024Generalized Coverage for More Robust Low-Budget Active Learningcited by 16
  8. 2024Uncertainty Herding: One Active Learning Method for All Label Budgetscited by 15
  9. 2023FreeAL: Towards Human-Free Active Learning in the Era of Large Language Modelscited by 14
  10. 2024Revisiting Active Learning in the Era of Vision Foundation Modelscited by 14
  11. 2024Making Better Use of Unlabelled Data in Bayesian Active Learningcited by 10
  12. 2023BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentationcited by 8
38 more
  1. 2024Querying Easily Flip-flopped Samples for Deep Active Learningcited by 7
  2. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  3. 2024Predicting the Susceptibility of Examples to Catastrophic Forgettingcited by 7
  4. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 7
  5. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  6. 2024Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Trainingcited by 6
  7. 2024Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classificationcited by 6
  8. 2024Deep Active Learning in the Open Worldcited by 5
  9. 2024Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrievalcited by 5
  10. 2024Feature Alignment: Rethinking Efficient Active Learning via Proxy in the Context of Pre-trained Modelscited by 4
  11. 2023NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coveragecited by 3
  12. 2023Learning to Rank for Active Learning via Multi-Task Bilevel Optimizationcited by 3
  13. 2024Class Balance Matters to Active Class-Incremental Learningcited by 3
  14. 2025Enhancing Cost Efficiency in Active Learning with Candidate Set Querycited by 3
  15. 2025Active Learning with a Noisy Annotatorcited by 3
  16. 2025Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspectivecited by 3
  17. 2024SUPClust: Active Learning at the Boundariescited by 2
  18. 2024DCoM: Active Learning for All Learnerscited by 2
  19. 2024Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Modelcited by 2
  20. 2024Active Prompt Learning with Vision-Language Model Priorscited by 2
  21. 2025To Label or Not to Label: PALM -- A Predictive Model for Evaluating Sample Efficiency in Active Learning Modelscited by 2
  22. 2026VIOLA: Towards Video In-Context Learning with Minimal Annotationscited by 2
  23. 2023Exploring Active Learning in Meta-Learning: Enhancing Context Set Labelingcited by 1
  24. 2025No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Successcited by 1
  25. 2025MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysiscited by 1
  26. 2026A Mechanism-Driven Theory of Phase Transitions in Active Learningcited by 1
  27. 2023VeML: An End-to-End Machine Learning Lifecycle for Large-scale and High-dimensional Datacited by 0
  28. 2023Fair Graph Machine Learning under Adversarial Missingness Processescited by 0
  29. 2024Diverse Subset Selection via Norm-Based Sampling and Orthogonalitycited by 0
  30. 2025PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Modelscited by 0
  31. 2025Cold-Start Active Preference Learning in Socio-Economic Domainscited by 0
  32. 2025Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classificationcited by 0
  33. 2025Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentationcited by 0
  34. 2025Active Learning with Task-Driven Representations for Messy Poolscited by 0
  35. 2025Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networkscited by 0
  36. 2025Offline Behavioral Data Selectioncited by 0
  37. 2026Conformal Cross-Modal Active Learningcited by 0
  38. 2026Random Is Hard to Beat: Active Selection in online DPO with Modern LLMscited by 0

50 most cited of 66 All 66 (JSON)