# On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications

arXiv: https://arxiv.org/abs/2111.09838 · HTML: https://mlsanity.com/paper/2111.09838/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 17 references that are in the map.
- First posted on arXiv 11 Nov 2021.

## Builds on (most cited first, 13 of 13)

- [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)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [DropBlock: A regularization method for convolutional networks](https://mlsanity.com/paper/1810.12890/) (2018)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Training independent subnetworks for robust prediction](https://mlsanity.com/paper/2010.06610/) (2020)
- [AutoDropout: Learning Dropout Patterns to Regularize Deep Networks](https://mlsanity.com/paper/2101.01761/) (2021)
- [URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks](https://mlsanity.com/paper/2007.04466/) (2020)
- [Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts](https://mlsanity.com/paper/2009.02967/) (2020)

## Built on by (most cited first, 2 of 2)

- [Tiny Deep Ensemble: Uncertainty Estimation in Edge AI Accelerators via Ensembling Normalization Layers with Shared Weights](https://mlsanity.com/paper/2405.05286/) (2024)
- [Concurrent Self-testing of Neural Networks Using Uncertainty Fingerprint](https://mlsanity.com/paper/2401.01458/) (2024)

## Abstract (arXiv)

Deep neural networks have shown great success in prediction quality while reliable and robust uncertainty estimation remains a challenge. Predictive uncertainty supplements model predictions and enables improved functionality of downstream tasks including embedded and mobile applications, such as virtual reality, augmented reality, sensor fusion, and perception. These applications often require a compromise in complexity to obtain uncertainty estimates due to very limited memory and compute resources. We tackle this problem by building upon Monte Carlo Dropout (MCDO) models using the Axolotl framework; specifically, we diversify sampled subnetworks, leverage dropout patterns, and use a branching technique to improve predictive performance while maintaining fast computations. We conduct experiments on (1) a multi-class classification task using the CIFAR10 dataset, and (2) a more complex human body segmentation task. Our results show the effectiveness of our approach by reaching close to Deep Ensemble prediction quality and uncertainty estimation, while still achieving faster inference on resource-limited mobile platforms.