# Uncertainty Surrogates for Deep Learning

arXiv: https://arxiv.org/abs/2104.08147 · HTML: https://mlsanity.com/paper/2104.08147/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks](https://mlsanity.com/paper/1502.05336/) (2015)
- [Training independent subnetworks for robust prediction](https://mlsanity.com/paper/2010.06610/) (2020)
- [Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors](https://mlsanity.com/paper/2005.07186/) (2020)
- [High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach](https://mlsanity.com/paper/1802.07167/) (2018)
- [Masksembles for Uncertainty Estimation](https://mlsanity.com/paper/2012.08334/) (2020)
- [Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?](https://mlsanity.com/paper/1810.09102/) (2018)
- [A causal framework for explaining the predictions of black-box sequence-to-sequence models](https://mlsanity.com/paper/1707.01943/) (2017)
- [Deep and Confident Prediction for Time Series at Uber](https://mlsanity.com/paper/1709.01907/) (2017)
- [Hydra: Preserving Ensemble Diversity for Model Distillation](https://mlsanity.com/paper/2001.04694/) (2020)
- [Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes](https://mlsanity.com/paper/1805.05396/) (2018)
- [Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel](https://mlsanity.com/paper/1906.00588/) (2019)
- [A Less Biased Evaluation of Out-of-distribution Sample Detectors](https://mlsanity.com/paper/1809.04729/) (2018)
- [Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians](https://mlsanity.com/paper/1910.12288/) (2019)
- [Prior Networks for Detection of Adversarial Attacks](https://mlsanity.com/paper/1812.02575/) (2018)

## Abstract (arXiv)

In this paper we introduce a novel way of estimating prediction uncertainty in deep networks through the use of uncertainty surrogates. These surrogates are features of the penultimate layer of a deep network that are forced to match predefined patterns. The patterns themselves can be, among other possibilities, a known visual symbol. We show how our approach can be used for estimating uncertainty in prediction and out-of-distribution detection. Additionally, the surrogates allow for interpretability of the ability of the deep network to learn and at the same time lend robustness against adversarial attacks. Despite its simplicity, our approach is superior to the state-of-the-art approaches on standard metrics as well as computational efficiency and ease of implementation. A wide range of experiments are performed on standard datasets to prove the efficacy of our approach.