mlsanityData to 14 Oct 2026

Generalized Coverage for More Robust Low-Budget Active Learning

arXiv 2407.12212 ↗First posted 16 Jul 2024cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

The ProbCover method of Yehuda et al. is a well-motivated algorithm for active learning in low-budget regimes, which attempts to "cover" the data distribution with balls of a given radius at selected data points. We demonstrate, however, that the performance of this algorithm is extremely sensitive to the choice of this radius hyper-parameter, and that tuning it is quite difficult, with the original heuristic frequently failing. We thus introduce (and theoretically motivate) a generalized notion of "coverage," including ProbCover's objective as a special case, but also allowing smoother notions that are far more robust to hyper-parameter choice. We propose an efficient greedy method to optimize this coverage, generalizing ProbCover's algorithm; due to its close connection to kernel herding, we call it "MaxHerding." The objective can also be optimized non-greedily through a variant of k-medoids, clarifying the relationship to other low-budget active learning methods. In comprehensive experiments, MaxHerding surpasses existing active learning methods across multiple low-budget image classification benchmarks, and does so with less computational cost than most competitive methods.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 22 of its 61 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

22 of 61 references.

References · 22

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  4. 2017The Implicit Bias of Gradient Descent on Separable Datacited by 655
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  6. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  7. 2020SCAN: Learning to Classify Images without Labelscited by 352
  8. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  9. 2022Active Learning Through a Covering Lenscited by 66
  10. 2022Active Learning by Feature Mixingcited by 63
  11. 2018Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithmscited by 44
  12. 2018Stein Pointscited by 43
10 more
  1. 2020Fast and Eager k-Medoids Clustering: O(k) Runtime Improvement of the PAM, CLARA, and CLARANS Algorithmscited by 36
  2. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  3. 2021Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approachcited by 34
  4. 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 31
  5. 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
  6. 2016Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changescited by 18
  7. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 17
  8. 2021On Data Efficiency of Meta-learningcited by 16
  9. 2015Active Distance-Based Clustering using K-medoidscited by 8
  10. 2023Exploring Active Learning in Meta-Learning: Enhancing Context Set Labelingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 10.

16 papers.

Sort:

  1. 2024Uncertainty Herding: One Active Learning Method for All Label Budgetscited by 15
  2. 2025Active Learning with a Noisy Annotatorcited by 3
  3. 2025A2LC: Active and Automated Label Correction for Semantic Segmentationcited by 2
  4. 2025Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learningcited by 2
  5. 2025Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classificationcited by 0
  6. 2025Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentationcited by 0
  7. 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalancecited by 0
  8. 2026Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Bufferscited by 0
  9. 2026Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelinescited by 0
  10. 2026Group-invariant Coresets for Data-efficient Active Learningcited by 0
  11. 2026One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learningcited by 0
  12. 2026SUGFW+: An Uncertainty-guided Feature Weighting Framework for Cold Start Active Adaptation of SAM in Medical Image Segmentationcited by 0
4 more
  1. 2026Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Trackingcited by 0
  2. 2026Coordination on a Budget: Federated Active Learning with Few Labelscited by 0
  3. 2026Low-Budget Active Learning through Entropic Optimal Transportcited by 0
  4. 2026Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coveragecited by 0