mlsanityData to 7 Oct 2026

Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows

arXiv 2402.06537 ↗First posted 9 Feb 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is a critical task for safe deployment of learning systems in the open world setting. In this work, we investigate the use of feature density estimation via normalizing flows for OOD detection and present a fully unsupervised approach which requires no exposure to OOD data, avoiding researcher bias in OOD sample selection. This is a post-hoc method which can be applied to any pretrained model, and involves training a lightweight auxiliary normalizing flow model to perform the out-of-distribution detection via density thresholding. Experiments on OOD detection in image classification show strong results for far-OOD data detection with only a single epoch of flow training, including 98.2% AUROC for ImageNet-1k vs. Textures, which exceeds the state of the art by 7.8%. We additionally explore the connection between the feature space distribution of the pretrained model and the performance of our method. Finally, we provide insights into training pitfalls that have plagued normalizing flows for use in OOD detection.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

28 of 39 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2013Describing Textures in the Wildcited by 2,110
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  12. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
16 more
  1. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  2. 2020Understanding the Behaviour of Contrastive Losscited by 397
  3. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  4. 2019Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Designcited by 258
  5. 2019Residual Flows for Invertible Generative Modelingcited by 256
  6. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  7. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  8. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  11. 2020Hybrid Models for Open Set Recognitioncited by 109
  12. 2022Denoising diffusion models for out-of-distribution detectioncited by 102
  13. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  14. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
  15. 2020Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Featurescited by 23
  16. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Probability Density from Latent Diffusion Models for Out-of-Distribution Detectioncited by 2
  2. 2025Breaking the Adversarial Robustness-Performance Trade-off in Text Classification via Manifold Purificationcited by 0
  3. 2026Image Quality Dependent Degradation for AI Systemscited by 0
  4. 2026Vmem-varphi: Low-Compute Out-of-Distribution Detection in Spiking Neural Networks from Membrane-Potential Statisticscited by 0