# Decomposing Representations for Deterministic Uncertainty Estimation

arXiv: https://arxiv.org/abs/2112.00856 · HTML: https://mlsanity.com/paper/2112.00856/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 7 of 7)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Invertible Residual Networks](https://mlsanity.com/paper/1811.00995/) (2018)
- [A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection](https://mlsanity.com/paper/2106.09022/) (2021)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)
- [Excessive Invariance Causes Adversarial Vulnerability](https://mlsanity.com/paper/1811.00401/) (2018)
- [Why is the Mahalanobis Distance Effective for Anomaly Detection?](https://mlsanity.com/paper/2003.00402/) (2020)

## Built on by (most cited first, 1 of 1)

- [Two-step counterfactual generation for OOD examples](https://mlsanity.com/paper/2302.05196/) (2023)

## Abstract (arXiv)

Uncertainty estimation is a key component in any deployed machine learning system. One way to evaluate uncertainty estimation is using "out-of-distribution" (OoD) detection, that is, distinguishing between the training data distribution and an unseen different data distribution using uncertainty. In this work, we show that current feature density based uncertainty estimators cannot perform well consistently across different OoD detection settings. To solve this, we propose to decompose the learned representations and integrate the uncertainties estimated on them separately. Through experiments, we demonstrate that we can greatly improve the performance and the interpretability of the uncertainty estimation.