# Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation

arXiv: https://arxiv.org/abs/2007.08128 · HTML: https://mlsanity.com/paper/2007.08128/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution](https://mlsanity.com/paper/2405.09800/) (2024)
- [HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router](https://mlsanity.com/paper/2410.02684/) (2024)
- [Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation](https://mlsanity.com/paper/2109.14885/) (2021)
- [Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2310.17432/) (2023)
- [CVAD: A generic medical anomaly detector based on Cascade VAE](https://mlsanity.com/paper/2110.15811/) (2021)
- [eVAE: Evolutionary Variational Autoencoder](https://mlsanity.com/paper/2301.00011/) (2023)
- [Brain-inspired continual pre-trained learner via silent synaptic consolidation](https://mlsanity.com/paper/2410.05899/) (2024)
- [Deep Auto-encoder with Neural Response](https://mlsanity.com/paper/2111.15309/) (2021)
- [What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization](https://mlsanity.com/paper/2207.05161/) (2022)
- [BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture](https://mlsanity.com/paper/2309.08036/) (2023)
- [DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories](https://mlsanity.com/paper/2502.16725/) (2025)
- [Out-of-Distribution Radar Detection in Compound Clutter and Thermal Noise through Variational Autoencoders](https://mlsanity.com/paper/2503.04861/) (2025)
- [Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models](https://mlsanity.com/paper/2106.07903/) (2021)
- [Autoencoder Attractors for Uncertainty Estimation](https://mlsanity.com/paper/2204.00382/) (2022)
- [Machine Learning Applications on Neuroimaging for Diagnosis and Prognosis of Epilepsy: A Review](https://mlsanity.com/paper/2102.03336/) (2021)
- [EmoGene: Audio-Driven Emotional 3D Talking-Head Generation](https://mlsanity.com/paper/2410.17262/) (2024)
- [The Exponentially Tilted Gaussian Prior for Variational Autoencoders](https://mlsanity.com/paper/2111.15646/) (2021)
- [Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening Mammogram](https://mlsanity.com/paper/2409.11534/) (2024)
- [RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis](https://mlsanity.com/paper/2508.12163/) (2025)
- [Out-of-Distribution Radar Detection with Complex VAEs: Theory, Whitening, and ANMF Fusion](https://mlsanity.com/paper/2601.18677/) (2026)
- [Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation](https://mlsanity.com/paper/2602.09581/) (2026)
- [UnGAP: Uncertainty-Guided Affine Prompting for Real-Time Crack Segmentation](https://mlsanity.com/paper/2605.02380/) (2026)

## Abstract (arXiv)

Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to out-of-distribution (OOD) inputs than in-distribution (ID) inputs. To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs. In this study, we propose an improved noise contrastive prior (INCP) to be able to integrate into the encoder of VAEs, called INCPVAE. INCP is scalable, trainable and compatible with VAEs, and it also adopts the merits from the INCP for uncertainty estimation. Experiments on various datasets demonstrate that compared to the standard VAEs, our model is superior in uncertainty estimation for the OOD data and is robust in anomaly detection tasks. The INCPVAE model obtains reliable uncertainty estimation for OOD inputs and solves the OOD problem in VAE models.