# Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks

arXiv: https://arxiv.org/abs/2308.00231 · HTML: https://mlsanity.com/paper/2308.00231/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 1 Aug 2023.

## Builds on (most cited first, 22 of 22)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Why Is My Classifier Discriminatory?](https://mlsanity.com/paper/1805.12002/) (2018)
- [Plex: Towards Reliability using Pretrained Large Model Extensions](https://mlsanity.com/paper/2207.07411/) (2022)
- [Urban Driving with Conditional Imitation Learning](https://mlsanity.com/paper/1912.00177/) (2019)
- [Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning](https://mlsanity.com/paper/2106.04015/) (2021)
- [Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation](https://mlsanity.com/paper/2106.12387/) (2021)
- [Edward: A library for probabilistic modeling, inference, and criticism](https://mlsanity.com/paper/1610.09787/) (2016)
- [DVI: Depth Guided Video Inpainting for Autonomous Driving](https://mlsanity.com/paper/2007.08854/) (2020)
- [ZhuSuan: A Library for Bayesian Deep Learning](https://mlsanity.com/paper/1709.05870/) (2017)

## Abstract (arXiv)

The modern pervasiveness of large-scale deep neural networks (NNs) is driven by their extraordinary performance on complex problems but is also plagued by their sudden, unexpected, and often catastrophic failures, particularly on challenging scenarios. Existing algorithms that provide risk-awareness to NNs are complex and ad-hoc. Specifically, these methods require significant engineering changes, are often developed only for particular settings, and are not easily composable. Here we present capsa, a framework for extending models with risk-awareness. Capsa provides a methodology for quantifying multiple forms of risk and composing different algorithms together to quantify different risk metrics in parallel. We validate capsa by implementing state-of-the-art uncertainty estimation algorithms within the capsa framework and benchmarking them on complex perception datasets. We demonstrate capsa's ability to easily compose aleatoric uncertainty, epistemic uncertainty, and bias estimation together in a single procedure, and show how this approach provides a comprehensive awareness of NN risk.