mlsanityData to 7 Oct 2026

Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning

arXiv 2210.07805 ↗First posted 13 Oct 2022cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Unlabeled data examples awaiting annotations contain open-set noise inevitably. A few active learning studies have attempted to deal with this open-set noise for sample selection by filtering out the noisy examples. However, because focusing on the purity of examples in a query set leads to overlooking the informativeness of the examples, the best balancing of purity and informativeness remains an important question. In this paper, to solve this purity-informativeness dilemma in open-set active learning, we propose a novel Meta-Query-Net,(MQ-Net) that adaptively finds the best balancing between the two factors. Specifically, by leveraging the multi-round property of active learning, we train MQ-Net using a query set without an additional validation set. Furthermore, a clear dominance relationship between unlabeled examples is effectively captured by MQ-Net through a novel skyline regularization. Extensive experiments on multiple open-set active learning scenarios demonstrate that the proposed MQ-Net achieves 20.14% improvement in terms of accuracy, compared with the state-of-the-art methods.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 30 of its 59 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

30 of 59 references.

References · 30

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  6. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  9. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  10. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  11. 2020A Survey of Deep Active Learningcited by 547
  12. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
18 more
  1. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  2. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  3. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  4. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  5. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  6. 2019Learning Loss for Active Learningcited by 335
  7. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  8. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  9. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  10. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  11. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  12. 2021Batch Active Learning at Scalecited by 127
  13. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  14. 2018NSML: Meet the MLaaS platform with a real-world case studycited by 70
  15. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  16. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  17. 2021Removing Undesirable Feature Contributions Using Out-of-Distribution Datacited by 23
  18. 2017A Survey of Skyline Query Processingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 9; 2025: 6; 2026: 4.

24 papers.

Sort:

By area:

  1. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  2. 2023Continuous Learning for Android Malware Detectioncited by 33
  3. 2024Active Generalized Category Discoverycited by 31
  4. 2023Entropic Open-set Active Learningcited by 22
  5. 2023Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracycited by 20
  6. 2024LEGO-Learn: Label-Efficient Graph Open-Set Learningcited by 10
  7. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7
  8. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 6
  9. 2024Inconsistency-Based Data-Centric Active Open-Set Annotationcited by 5
  10. 2025Active Learning for Continual Learning: Keeping the Past Alive in the Presentcited by 5
  11. 2025Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approachcited by 5
  12. 2025Enhancing Cost Efficiency in Active Learning with Candidate Set Querycited by 3
12 more
  1. 2023Training Ensembles with Inliers and Outliers for Semi-supervised Active Learningcited by 2
  2. 2023How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learningcited by 2
  3. 2024Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Modelcited by 1
  4. 2024AutoAL: Automated Active Learning with Differentiable Query Strategy Searchcited by 1
  5. 2025ALScope: A Unified Toolkit for Deep Active Learningcited by 1
  6. 2024Prioritizing Informative Features and Examples for Deep Learning from Noisy Datacited by 0
  7. 2024Dirichlet-Based Coarse-to-Fine Example Selection For Open-Set Annotationcited by 0
  8. 2025SAMOSA: Sharpness Aware Minimization for Open Set Active learningcited by 0
  9. 2026Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learningcited by 0
  10. 2026Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignmentcited by 0
  11. 2026Energy-Based Open-Set Active Learning for Object Classificationcited by 0
  12. 2026RTLCurator: Label-Efficient Data Curation for RTL Generationcited by 0