Data to 7 Oct 2026

Likelihood Ratios for Out-of-Distribution Detection

arXiv 1906.02845 ↗First posted 7 Jun 2019stat.ML cs.LGcited by 451

Not on the map. Why?

Abstract (arXiv)

Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not present in the training data. We introduce a genomics dataset for OOD detection that allows other researchers to benchmark progress on this important problem. We investigate deep generative model based approaches for OOD detection and observe that the likelihood score is heavily affected by population level background statistics. We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics. We benchmark the OOD detection performance of the proposed method against existing approaches on the genomics dataset and show that our method achieves state-of-the-art performance. We demonstrate the generality of the proposed method by showing that it significantly improves OOD detection when applied to deep generative models of images.

Key facts. Cited by 451 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 112; 2022: 117; 2023: 71; 2024: 64; 2025: 54; 2026: 33.

451 papers.

Sort:

By area:

2021Generalized Out-of-Distribution Detection: A Surveycited by 796
2021A Survey of Uncertainty in Deep Neural Networkscited by 675
2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2021GAN Inversion: A Surveycited by 366
2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206

38 more

2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
2022Is Out-of-Distribution Detection Learnable?cited by 109
2021Semantically Coherent Out-of-Distribution Detectioncited by 107
2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
2021Model-Based Domain Generalizationcited by 103
2022Denoising diffusion models for out-of-distribution detectioncited by 102
2021Can multi-label classification networks know what they don't know?cited by 100
2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
2021Constraints Penalized Q-learning for Safe Offline Reinforcement Learningcited by 90
2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 67
2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 67
2024Variational Bayesian Last Layerscited by 67
2021What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?cited by 63
2022Full-Spectrum Out-of-Distribution Detectioncited by 63
2021Hierarchical VAEs Know What They Don't Knowcited by 58
2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
2021Rectangular Flows for Manifold Learningcited by 49
2021Densely connected normalizing flowscited by 49
2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
2024A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)cited by 44
2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42

50 most cited of 451 All 451 (JSON)