Revisiting Neural Activation Coverage for Uncertainty Estimation
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 12 references that are in the map. First posted on arXiv 24 Apr 2026.
Builds on
9 of 12 references.
References · 9
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2017Self-Normalizing Neural Networkscited by 591
- 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
- 2023Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalizationcited by 28
- 2019Density estimation in representation space to predict model uncertaintycited by 27
- 2021An Introduction to Variational Inferencecited by 11
Built on by
Not cited yet.