mlsanityData to 7 Oct 2026

Input complexity and out-of-distribution detection with likelihood-based generative models

arXiv 1909.11480 ↗First posted 25 Sep 2019cs.LG stat.MLcited by 186

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Likelihood-based generative models are a promising resource to detect out-of-distribution (OOD) inputs which could compromise the robustness or reliability of a machine learning system. However, likelihoods derived from such models have been shown to be problematic for detecting certain types of inputs that significantly differ from training data. In this paper, we pose that this problem is due to the excessive influence that input complexity has in generative models' likelihoods. We report a set of experiments supporting this hypothesis, and use an estimate of input complexity to derive an efficient and parameter-free OOD score, which can be seen as a likelihood-ratio, akin to Bayesian model comparison. We find such score to perform comparably to, or even better than, existing OOD detection approaches under a wide range of data sets, models, model sizes, and complexity estimates.

Key facts. Cited by 186 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 45; 2023: 30; 2024: 38; 2025: 19; 2026: 16.

186 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  3. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  4. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  5. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  6. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  7. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  8. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  9. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  10. 2022Denoising diffusion models for out-of-distribution detectioncited by 102
  11. 2021Can multi-label classification networks know what they don't know?cited by 100
  12. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
38 more
  1. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  2. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  3. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  4. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  5. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  6. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  7. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
  8. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  9. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
  10. 2023Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEscited by 54
  11. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  12. 2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
  13. 2024A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)cited by 44
  14. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 43
  15. 2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
  16. 2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
  17. 2023Maskomaly:Zero-Shot Mask Anomaly Segmentationcited by 34
  18. 2021Autoencoders for unsupervised anomaly detection in high energy physicscited by 32
  19. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 32
  20. 2021A Style and Semantic Memory Mechanism for Domain Generalizationcited by 32
  21. 2025Energy-Based Transformers are Scalable Learners and Thinkerscited by 30
  22. 2022Watermarking for Out-of-distribution Detectioncited by 28
  23. 2021OODformer: Out-Of-Distribution Detection Transformercited by 27
  24. 2021Autoencoding Under Normalization Constraintscited by 26
  25. 2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 25
  26. 2023MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detectioncited by 25
  27. 2022Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learningcited by 24
  28. 2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23
  29. 2023Distribution Shift Inversion for Out-of-Distribution Predictioncited by 23
  30. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  31. 2023Unsupervised 3D out-of-distribution detection with latent diffusion modelscited by 22
  32. 2024A Geometric Explanation of the Likelihood OOD Detection Paradoxcited by 22
  33. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Modelcited by 22
  34. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  35. 2022How Useful are Gradients for OOD Detection Really?cited by 20
  36. 2024Self-Guided Generation of Minority Samples Using Diffusion Modelscited by 19
  37. 2024Minority-Focused Text-to-Image Generation via Prompt Optimizationcited by 18
  38. 2021On Out-of-distribution Detection with Energy-based Modelscited by 17

50 most cited of 186 All 186 (JSON)