mlsanityData to 14 Oct 2026

Falsehoods that ML researchers believe about OOD detection

arXiv 2210.12767 ↗First posted 23 Oct 2022stat.ML cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

An intuitive way to detect out-of-distribution (OOD) data is via the density function of a fitted probabilistic generative model: points with low density may be classed as OOD. But this approach has been found to fail, in deep learning settings. In this paper, we list some falsehoods that machine learning researchers believe about density-based OOD detection. Many recent works have proposed likelihood-ratio-based methods to `fix' the problem. We propose a framework, the OOD proxy framework, to unify these methods, and we argue that likelihood ratio is a principled method for OOD detection and not a mere `fix'. Finally, we discuss the relationship between domain discrimination and semantics.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 14 of its 19 references that are in the map. First posted on arXiv 23 Oct 2022.

Builds on

14 of 19 references.

References · 14

  1. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  3. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  5. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  6. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  8. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  9. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  10. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  11. 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
  12. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 33
2 more
  1. 2019Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicalitycited by 31
  2. 2022Out-of-Distribution Detection with Class Ratio Estimationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 2; 2026: 1.

8 papers.

  1. 2025Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Artcited by 13
  2. 2024A Likelihood Ratio-Based Approach to Segmenting Unknown Objectscited by 12
  3. 2024Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detectorcited by 11
  4. 2023FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Scorecited by 5
  5. 2024Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratioscited by 3
  6. 2025Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detectioncited by 3
  7. 2023SR-OOD: Out-of-Distribution Detection via Sample Repairingcited by 1
  8. 2026Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrievalcited by 0