mlsanityData to 7 Oct 2026

Uncertainty Herding: One Active Learning Method for All Label Budgets

arXiv 2412.20644 ↗First posted 30 Dec 2024cs.LG stat.MLcited by 12

Not on the map. Why?

Abstract (arXiv)

Most active learning research has focused on methods which perform well when many labels are available, but can be dramatically worse than random selection when label budgets are small. Other methods have focused on the low-budget regime, but do poorly as label budgets increase. As the line between "low" and "high" budgets varies by problem, this is a serious issue in practice. We propose uncertainty coverage, an objective which generalizes a variety of low- and high-budget objectives, as well as natural, hyperparameter-light methods to smoothly interpolate between low- and high-budget regimes. We call greedy optimization of the estimate Uncertainty Herding; this simple method is computationally fast, and we prove that it nearly optimizes the distribution-level coverage. In experimental validation across a variety of active learning tasks, our proposal matches or beats state-of-the-art performance in essentially all cases; it is the only method of which we are aware that reliably works well in both low- and high-budget settings.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

28 of 58 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2019A Closer Look at Few-shot Classificationcited by 679
  9. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  10. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  11. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  12. 2019Diverse mini-batch Active Learningcited by 88
16 more
  1. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  2. 2022Active Learning by Feature Mixingcited by 63
  3. 2022Active Learning Through a Covering Lenscited by 62
  4. 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
  5. 2018Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithmscited by 44
  6. 2019Batch Active Learning Using Determinantal Point Processescited by 42
  7. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  8. 2020Fast and Eager k-Medoids Clustering: O(k) Runtime Improvement of the PAM, CLARA, and CLARANS Algorithmscited by 35
  9. 2021Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approachcited by 34
  10. 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
  11. 2016Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changescited by 18
  12. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
  13. 2024Generalized Coverage for More Robust Low-Budget Active Learningcited by 15
  14. 2022TiDAL: Learning Training Dynamics for Active Learningcited by 11
  15. 2015Active Distance-Based Clustering using K-medoidscited by 8
  16. 2024Bridging Diversity and Uncertainty in Active learning with Self-Supervised Pre-Trainingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 9.

12 papers.

  1. 2025Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learningcited by 2
  2. 2026A Mechanism-Driven Theory of Phase Transitions in Active Learningcited by 1
  3. 2025Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classificationcited by 0
  4. 2025Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentationcited by 0
  5. 2026Conformal Cross-Modal Active Learningcited by 0
  6. 2026Random Is Hard to Beat: Active Selection in online DPO with Modern LLMscited by 0
  7. 2026Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelinescited by 0
  8. 2026One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learningcited by 0
  9. 2026How Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classificationcited by 0
  10. 2026Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noisecited by 0
  11. 2026SUGFW+: An Uncertainty-guided Feature Weighting Framework for Cold Start Active Adaptation of SAM in Medical Image Segmentationcited by 0
  12. 2026Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Trackingcited by 0