mlsanityData to 14 Oct 2026

MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space

arXiv 2105.01879 ↗First posted 5 May 2021cs.CV cs.LGcited by 233

Not on the map. Why?

Cited by 22 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world. Existing solutions are mainly driven by small datasets, with low resolution and very few class labels (e.g., CIFAR). As a result, OOD detection for large-scale image classification tasks remains largely unexplored. In this paper, we bridge this critical gap by proposing a group-based OOD detection framework, along with a novel OOD scoring function termed MOS. Our key idea is to decompose the large semantic space into smaller groups with similar concepts, which allows simplifying the decision boundaries between in- vs. out-of-distribution data for effective OOD detection. Our method scales substantially better for high-dimensional class space than previous approaches. We evaluate models trained on ImageNet against four carefully curated OOD datasets, spanning diverse semantics. MOS establishes state-of-the-art performance, reducing the average FPR95 by 14.33% while achieving 6x speedup in inference compared to the previous best method.

Key facts. Cited by 233 papers in the map (data through 14 Oct 2026). Builds on 34 of its 55 references that are in the map. First posted on arXiv 5 May 2021.

Builds on

34 of 55 references.

References · 34

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2013Describing Textures in the Wildcited by 2,125
  6. 2016Density estimation using Real NVPcited by 2,042
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  9. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
22 more
  1. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  2. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  3. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  6. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  7. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  8. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  9. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
  10. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  11. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  12. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  13. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  14. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  15. 2017Hard Mixtures of Experts for Large Scale Weakly Supervised Visioncited by 67
  16. 2016Network of Experts for Large-Scale Image Categorizationcited by 54
  17. 2018Discriminative out-of-distribution detection for semantic segmentationcited by 47
  18. 2019Generating Multiple Objects at Spatially Distinct Locationscited by 41
  19. 2018WAIC, but Why? Generative Ensembles for Robust Anomaly Detectioncited by 25
  20. 2017Confidence estimation in Deep Neural networks via density modellingcited by 7
  21. 2019Are Out-of-Distribution Detection Methods Effective on Large-Scale Datasets?cited by 6
  22. 2014Self-informed neural network structure learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 36; 2023: 68; 2024: 51; 2025: 51; 2026: 17.

233 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  5. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  6. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  7. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  8. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  9. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  10. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  11. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  12. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
38 more
  1. 2023Non-Parametric Outlier Synthesiscited by 129
  2. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  3. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  4. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  5. 2024ARGS: Alignment as Reward-Guided Searchcited by 103
  6. 2021Can multi-label classification networks know what they don't know?cited by 100
  7. 2024Process Reward Model with Q-Value Rankingscited by 80
  8. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  9. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  10. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  11. 2023Nearest Neighbor Guidance for Out-of-Distribution Detectioncited by 64
  12. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  13. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  14. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 49
  15. 2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
  16. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  17. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  18. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  19. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  20. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  21. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  22. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  23. 2023GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detectioncited by 36
  24. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  25. 2023LINe: Out-of-Distribution Detection by Leveraging Important Neuronscited by 34
  26. 2023Detecting Out-of-Distribution Through the Lens of Neural Collapsecited by 34
  27. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  28. 2022OpenCon: Open-world Contrastive Learningcited by 33
  29. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 32
  30. 2021No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasetscited by 31
  31. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  32. 2022Block Selection Method for Using Feature Norm in Out-of-distribution Detectioncited by 30
  33. 2022Watermarking for Out-of-distribution Detectioncited by 28
  34. 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
  35. 2022Augmenting Softmax Information for Selective Classification with Out-of-Distribution Datacited by 27
  36. 2023Understanding the Feature Norm for Out-of-Distribution Detectioncited by 27
  37. 2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 26
  38. 2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23

50 most cited of 233 All 233 (JSON)