# Revisiting Neural Activation Coverage for Uncertainty Estimation

arXiv: https://arxiv.org/abs/2604.22360 · HTML: https://mlsanity.com/paper/2604.22360/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Classification Uncertainty of Deep Neural Networks Based on Gradient Information](https://mlsanity.com/paper/1805.08440/) (2018)
- [Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2306.02879/) (2023)
- [Density estimation in representation space to predict model uncertainty](https://mlsanity.com/paper/1908.07235/) (2019)
- [An Introduction to Variational Inference](https://mlsanity.com/paper/2108.13083/) (2021)

## Abstract (arXiv)

Neural activation coverage (NAC) is a recently-proposed technique for out-of-distribution detection and generalization. We build upon this promising foundation and extend the method to work as an uncertainty estimation technique for already-trained artificial neural networks in the domain of regression. Our experiments confirm NAC uncertainty scores to be more meaningful than other techniques, e.g. Monte-Carlo Dropout.