Data to 7 Oct 2026

Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

arXiv 2003.02977 ↗First posted 6 Mar 2020cs.LG cs.CV stat.MLcited by 145

Not on the map. Why?

Abstract (arXiv)

Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood. However, some recent studies show that probabilistic generative models can, in some cases, assign higher likelihoods on certain types of OOD samples, making the OOD detection rules based on likelihood threshold problematic. To address this issue, several OOD detection methods have been proposed for deep generative models. In this paper, we make the observation that many of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). As an alternative, we propose Likelihood Regret, an efficient OOD score for VAEs. We benchmark our proposed method over existing approaches, and empirical results suggest that our method obtains the best overall OOD detection performances when applied to VAEs.

Key facts. Cited by 145 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 34; 2023: 31; 2024: 31; 2025: 19; 2026: 11.

145 papers.

Sort:

By area:

2021Generalized Out-of-Distribution Detection: A Surveycited by 796
2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
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
2022Denoising diffusion models for out-of-distribution detectioncited by 102
2021Can multi-label classification networks know what they don't know?cited by 100
2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
2021Hierarchical VAEs Know What They Don't Knowcited by 58

38 more

2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
2023Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEscited by 54
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
2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
2024A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)cited by 44
2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 43
2023Model-Based Runtime Monitoring with Interactive Imitation Learningcited by 37
2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 30
2022Watermarking for Out-of-distribution Detectioncited by 28
2021Autoencoding Under Normalization Constraintscited by 26
2021Conditional Image Generation by Conditioning Variational Auto-Encoderscited by 25
2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23
2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23
2024A Geometric Explanation of the Likelihood OOD Detection Paradoxcited by 22
2022Igeood: An Information Geometry Approach to Out-of-Distribution Detectioncited by 20
2022Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Modelcited by 18
2021Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?cited by 16
2021Entropic Issues in Likelihood-Based OOD Detectioncited by 16
2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
2022Model-agnostic out-of-distribution detection using combined statistical testscited by 14
2022Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projectioncited by 13
2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
2023Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Featurescited by 12
20223DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Cloudscited by 11
2022Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penaltycited by 11
2024Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adaptcited by 11
2026Foundational World Models Accurately Detect Bimanual Manipulator Failurescited by 11
2023Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Modelscited by 10
2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agentscited by 9
2023Model-free Test Time Adaptation for Out-Of-Distribution Detectioncited by 9
2023Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Modelscited by 9
2021Robust outlier detection by de-biasing VAE likelihoodscited by 8
2022Rethinking Out-of-Distribution Detection From a Human-Centric Perspectivecited by 7
2023Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videoscited by 7
2024Taming False Positives in Out-of-Distribution Detection with Human Feedbackcited by 7

50 most cited of 145 All 145 (JSON)