# Unsupervised Out-of-Distribution Detection with Batch Normalization

arXiv: https://arxiv.org/abs/1910.09115 · HTML: https://mlsanity.com/paper/1910.09115/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Knowing More About Questions Can Help: Improving Calibration in Question Answering](https://mlsanity.com/paper/2106.01494/) (2021)
- [MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2308.15300/) (2023)
- [Delving into the Estimation Shift of Batch Normalization in a Network](https://mlsanity.com/paper/2203.10778/) (2022)
- [Thinking in Groups: Permutation Tests Reveal Near-Out-of-Distribution](https://mlsanity.com/paper/2403.14058/) (2024)
- [DOI: Divergence-based Out-of-Distribution Indicators via Deep Generative Models](https://mlsanity.com/paper/2108.05509/) (2021)
- [The Exponentially Tilted Gaussian Prior for Variational Autoencoders](https://mlsanity.com/paper/2111.15646/) (2021)

## Abstract (arXiv)

Likelihood from a generative model is a natural statistic for detecting out-of-distribution (OoD) samples. However, generative models have been shown to assign higher likelihood to OoD samples compared to ones from the training distribution, preventing simple threshold-based detection rules. We demonstrate that OoD detection fails even when using more sophisticated statistics based on the likelihoods of individual samples. To address these issues, we propose a new method that leverages batch normalization. We argue that batch normalization for generative models challenges the traditional i.i.d. data assumption and changes the corresponding maximum likelihood objective. Based on this insight, we propose to exploit in-batch dependencies for OoD detection. Empirical results suggest that this leads to more robust detection for high-dimensional images.