mlsanityData to 14 Oct 2026

Deep Active Learning in the Open World

arXiv 2411.06353 ↗First posted 10 Nov 2024cs.LG cs.AI cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find application in safety-critical domains, effectively handling out-of-distribution (OOD) data is crucial to building open-world learning systems. In this work, we introduce ALOE, a novel active learning algorithm for open-world environments designed to enhance model adaptation by incorporating new OOD classes via a two-stage approach. First, diversity sampling selects a representative set of examples, followed by energy-based OOD detection to prioritize likely unknown classes for annotation. This strategy accelerates class discovery and learning, even under constrained annotation budgets. Evaluations on three long-tailed image classification benchmarks demonstrate that ALOE outperforms traditional active learning baselines, effectively expanding known categories while balancing annotation cost. Our findings reveal a crucial tradeoff between enhancing known-class performance and discovering new classes, setting the stage for future advancements in open-world machine learning.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 64 of its 87 references that are in the map. First posted on arXiv 10 Nov 2024.

Builds on

64 of 87 references.

References · 64

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2020Supervised Contrastive Learningcited by 2,829
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  8. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  9. 2017Deep Bayesian Active Learning with Image Datacited by 819
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  11. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
38 more
  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  2. 2015Towards Open Set Deep Networkscited by 538
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  6. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  7. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  8. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  9. 2014Towards Open World Recognitioncited by 226
  10. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  11. 2021Open-World Semi-Supervised Learningcited by 165
  12. 2021A Unified Objective for Novel Class Discoverycited by 162
  13. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  14. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  15. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  16. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 143
  17. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  18. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  19. 2021Batch Active Learning at Scalecited by 127
  20. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 121
  21. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  22. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  23. 2022A Comparative Survey of Deep Active Learningcited by 89
  24. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  25. 2022Training OOD Detectors in their Natural Habitatscited by 86
  26. 2017Deep Active Learning over the Long Tailcited by 84
  27. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
  28. 2022Active Learning Through a Covering Lenscited by 66
  29. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  30. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  31. 2019Batch Active Learning Using Determinantal Point Processescited by 43
  32. 2022Class-incremental Novel Class Discoverycited by 42
  33. 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learningcited by 37
  34. 2022Active Learning for Open-set Annotationcited by 34
  35. 2022OpenCon: Open-world Contrastive Learningcited by 33
  36. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  37. 2024Active Generalized Category Discoverycited by 31
  38. 2022GALAXY: Graph-based Active Learning at the Extremecited by 29

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Improving Task Diversity in Label Efficient Supervised Finetuning of LLMscited by 1
  2. 2025Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Directioncited by 0
  3. 2025Active Learning with Task-Driven Representations for Messy Poolscited by 0
  4. 2026SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classificationcited by 0
  5. 2026OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticismcited by 0