mlsanityData to 7 Oct 2026

DCoM: Active Learning for All Learners

arXiv 2407.01804 ↗First posted 1 Jul 2024cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Deep Active Learning (AL) techniques can be effective in reducing annotation costs for training deep models. However, their effectiveness in low- and high-budget scenarios seems to require different strategies, and achieving optimal results across varying budget scenarios remains a challenge. In this study, we introduce Dynamic Coverage & Margin mix (DCoM), a novel active learning approach designed to bridge this gap. Unlike existing strategies, DCoM dynamically adjusts its strategy, considering the competence of the current model. Through theoretical analysis and empirical evaluations on diverse datasets, including challenging computer vision tasks, we demonstrate DCoM's ability to overcome the cold start problem and consistently improve results across different budgetary constraints. Thus DCoM achieves state-of-the-art performance in both low- and high-budget regimes.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 25 of its 47 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

25 of 47 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  9. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  10. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  11. 2020SCAN: Learning to Classify Images without Labelscited by 351
  12. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
13 more
  1. 2021Solo-learn: A Library of Self-supervised Methods for Visual Representation Learningcited by 116
  2. 2019Discriminative Active Learningcited by 97
  3. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  4. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
  5. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  6. 2022Active Learning Through a Covering Lenscited by 62
  7. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
  8. 2023Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigmcited by 36
  9. 2021Active Learning for Deep Visual Trackingcited by 19
  10. 2023How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budgetcited by 16
  11. 2021Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principlecited by 14
  12. 2024Querying Easily Flip-flopped Samples for Deep Active Learningcited by 7
  13. 2023NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coveragecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025To Label or Not to Label: PALM -- A Predictive Model for Evaluating Sample Efficiency in Active Learning Modelscited by 2
  2. 2026One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learningcited by 0