mlsanityData to 7 Oct 2026

SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios

arXiv 2107.00717 ↗First posted 1 Jul 2021cs.LG cs.CVcited by 83

Not on the map. Why?

Abstract (arXiv)

Active learning has proven to be useful for minimizing labeling costs by selecting the most informative samples. However, existing active learning methods do not work well in realistic scenarios such as imbalance or rare classes, out-of-distribution data in the unlabeled set, and redundancy. In this work, we propose SIMILAR (Submodular Information Measures based actIve LeARning), a unified active learning framework using recently proposed submodular information measures (SIM) as acquisition functions. We argue that SIMILAR not only works in standard active learning, but also easily extends to the realistic settings considered above and acts as a one-stop solution for active learning that is scalable to large real-world datasets. Empirically, we show that SIMILAR significantly outperforms existing active learning algorithms by as much as ~5% - 18% in the case of rare classes and ~5% - 10% in the case of out-of-distribution data on several image classification tasks like CIFAR-10, MNIST, and ImageNet. SIMILAR is available as a part of the DISTIL toolkit: "https://github.com/decile-team/distil".

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Builds on 22 of its 47 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

22 of 47 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  8. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  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. 2015Adversarial Autoencoderscited by 359
  12. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
10 more
  1. 2013One Billion Word Benchmark for Measuring Progress in Statistical Language Modelingcited by 302
  2. 2019Variational Adversarial Active Learningcited by 284
  3. 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
  4. 2014Lazier Than Lazy Greedycited by 97
  5. 2020Submodular Combinatorial Information Measures with Applications in Machine Learningcited by 88
  6. 2019Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Visioncited by 64
  7. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  8. 2015Submodular Functions: from Discrete to Continous Domainscited by 24
  9. 2020Submodularity in Action: From Machine Learning to Signal Processing Applicationscited by 12
  10. 2019A Memoization Framework for Scaling Submodular Optimization to Large Scale Problemscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 19; 2023: 19; 2024: 26; 2025: 8; 2026: 9.

83 papers.

Sort:

By area:

  1. 2022DeepCore: A Comprehensive Library for Coreset Selection in Deep Learningcited by 146
  2. 2022A Comparative Survey of Deep Active Learningcited by 88
  3. 2024A Survey of Multimodal Large Language Model from A Data-centric Perspectivecited by 73
  4. 2023Data Pruning via Moving-one-Sample-outcited by 67
  5. 2023FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informationcited by 63
  6. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  7. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  8. 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
  9. 2022Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantitiescited by 28
  10. 2025A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advancescited by 28
  11. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  12. 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
38 more
  1. 2023Entropic Open-set Active Learningcited by 22
  2. 2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
  3. 2024SMART: Submodular Data Mixture Strategy for Instruction Tuningcited by 16
  4. 2022Fast Rates in Pool-Based Batch Active Learningcited by 15
  5. 2025Data Pruning by Information Maximizationcited by 14
  6. 2022Active Learning with Neural Networks: Insights from Nonparametric Statisticscited by 13
  7. 2023Black-Box Batch Active Learning for Regressioncited by 12
  8. 2023Data pruning and neural scaling laws: fundamental limitations of score-based algorithmscited by 11
  9. 2022Learning Neural Set Functions Under the Optimal Subset Oraclecited by 10
  10. 2023Gaussian Switch Sampling: A Second Order Approach to Active Learningcited by 10
  11. 2022CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classificationcited by 9
  12. 2023A Weighted K-Center Algorithm for Data Subset Selectioncited by 9
  13. 2024Beyond Efficiency: Molecular Data Pruning for Enhanced Generalizationcited by 9
  14. 2023Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Datacited by 8
  15. 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
  16. 2024Active Fine-Tuning of Multi-Task Policiescited by 8
  17. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  18. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  19. 2024Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classificationcited by 7
  20. 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
  21. 2022Active Data Discovery: Mining Unknown Data using Submodular Information Measurescited by 6
  22. 2024Out-of-Distribution Learning with Human Feedbackcited by 6
  23. 2024Language Model-Driven Data Pruning Enables Efficient Active Learningcited by 6
  24. 2022Neural Active Learning on Heteroskedastic Distributionscited by 5
  25. 2024Bayesian Active Learning for Semantic Segmentationcited by 5
  26. 2024Deep Active Learning in the Open Worldcited by 5
  27. 2024Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrievalcited by 5
  28. 2022Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discoverycited by 4
  29. 2023Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verificationcited by 4
  30. 2024AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasetscited by 4
  31. 2025Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detectioncited by 4
  32. 2022PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Informationcited by 3
  33. 2022Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarioscited by 3
  34. 2025Enhancing Cost Efficiency in Active Learning with Candidate Set Querycited by 3
  35. 2021Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealingcited by 2
  36. 2023Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptionscited by 2
  37. 2023STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settingscited by 2
  38. 2023Training Ensembles with Inliers and Outliers for Semi-supervised Active Learningcited by 2

50 most cited of 83 All 83 (JSON)