mlsanityData to 7 Oct 2026

A Unified Approach Towards Active Learning and Out-of-Distribution Detection

arXiv 2405.11337 ↗First posted 18 May 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled data. In this context, robust out-of-distribution (OOD) detection mechanisms are essential for handling data outside the target distribution of the application. However, current works investigate both problems separately. In this work, we introduce SISOM as the first unified solution for both AL and OOD detection. By leveraging feature space distance metrics SISOM combines the strengths of the currently independent tasks to solve both effectively. We conduct extensive experiments showing the problems arising when migrating between both tasks. In these evaluations SISOM underlined its effectiveness by achieving first place in two of the widely used OpenOOD benchmarks and second place in the remaining one. In AL, SISOM outperforms others and delivers top-1 performance in three benchmarks

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 70 of its 94 references that are in the map. First posted on arXiv 18 May 2024.

Builds on

70 of 94 references.

References · 70

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2013Describing Textures in the Wildcited by 2,110
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  12. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
38 more
  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  2. 2020A Survey of Deep Active Learningcited by 547
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  5. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  6. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  7. 2020SCAN: Learning to Classify Images without Labelscited by 351
  8. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  9. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  10. 2019Learning Loss for Active Learningcited by 335
  11. 2019Variational Adversarial Active Learningcited by 284
  12. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  13. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  14. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  15. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  16. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  17. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  18. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  19. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  20. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  21. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  22. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  23. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 123
  24. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  25. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  26. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  27. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  28. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  29. 2022Active Learning Through a Covering Lenscited by 62
  30. 2020State-Relabeling Adversarial Active Learningcited by 60
  31. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  32. 2017Between-class Learning for Image Classificationcited by 50
  33. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  34. 2018Efficient Uncertainty Estimation for Semantic Segmentation in Videoscited by 46
  35. 2020Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systemscited by 46
  36. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  37. 2019Semantic-Aware Scene Recognitioncited by 43
  38. 2020Out-of-Distribution Detection for Automotive Perceptioncited by 37

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 5.

7 papers.

  1. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  2. 2025OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionarycited by 16
  3. 2025Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentationcited by 7
  4. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 6
  5. 2025Effective Data Pruning through Score Extrapolationcited by 2
  6. 2024Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Modelcited by 0
  7. 2025A Machine Learning Perspective on Automated Driving Corner Casescited by 0