# Notes on the Behavior of MC Dropout

arXiv: https://arxiv.org/abs/2008.02627 · HTML: https://mlsanity.com/paper/2008.02627/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Uncertainty-Aware Machine Translation Evaluation](https://mlsanity.com/paper/2109.06352/) (2021)
- [Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving](https://mlsanity.com/paper/2107.04991/) (2021)
- [Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach](https://mlsanity.com/paper/2501.06878/) (2025)
- [What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization](https://mlsanity.com/paper/2207.05161/) (2022)
- [Bayesian neural networks for predicting uncertainty in full-field material response](https://mlsanity.com/paper/2406.14838/) (2024)
- [B-BACN: Bayesian Boundary-Aware Convolutional Network for Crack Characterization](https://mlsanity.com/paper/2302.06827/) (2023)
- [Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data](https://mlsanity.com/paper/2405.09817/) (2024)
- [Thermal Earth Model for the Conterminous United States Using an Interpolative Physics-Informed Graph Neural Network (InterPIGNN)](https://mlsanity.com/paper/2403.09961/) (2024)
- [Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantification](https://mlsanity.com/paper/2411.03334/) (2024)
- [Unreliable Uncertainty Estimates with Monte Carlo Dropout](https://mlsanity.com/paper/2512.14851/) (2025)
- [RBUE: A ReLU-Based Uncertainty Estimation Method of Deep Neural Networks](https://mlsanity.com/paper/2107.07197/) (2021)
- [Embedded Ensembles: Infinite Width Limit and Operating Regimes](https://mlsanity.com/paper/2202.12297/) (2022)
- [Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing](https://mlsanity.com/paper/2210.10526/) (2022)
- [Uncertainty Quantification for Deep Learning](https://mlsanity.com/paper/2405.20550/) (2024)
- [Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review](https://mlsanity.com/paper/2505.07911/) (2025)
- [A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysis](https://mlsanity.com/paper/2511.00301/) (2025)
- [Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference](https://mlsanity.com/paper/2511.21223/) (2025)
- [Amortised Inference in Bayesian Neural Networks](https://mlsanity.com/paper/2309.03018/) (2023)
- [Artificial Behavior Intelligence: Technology, Challenges, and Future Directions](https://mlsanity.com/paper/2505.03315/) (2025)
- [Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models](https://mlsanity.com/paper/2505.15934/) (2025)
- [Convergence, design and training of continuous-time dropout as a random batch method](https://mlsanity.com/paper/2510.13134/) (2025)
- [A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning](https://mlsanity.com/paper/2605.16570/) (2026)
- [Rethinking Epistemic Uncertainty in Node Classification through Information Growth](https://mlsanity.com/paper/2610.03418/) (2026)

## Abstract (arXiv)

Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.