# Scalable Uncertainty for Computer Vision with Functional Variational Inference

arXiv: https://arxiv.org/abs/2003.03396 · HTML: https://mlsanity.com/paper/2003.03396/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 12 of 12)

- [Tractable Function-Space Variational Inference in Bayesian Neural Networks](https://mlsanity.com/paper/2312.17199/) (2023)
- [Hyperbolic Active Learning for Semantic Segmentation under Domain Shift](https://mlsanity.com/paper/2306.11180/) (2023)
- [Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes](https://mlsanity.com/paper/2109.09690/) (2021)
- [Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks](https://mlsanity.com/paper/2306.05674/) (2023)
- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning](https://mlsanity.com/paper/2304.04824/) (2023)
- [Attentive Continuous Generative Self-training for Unsupervised Domain Adaptive Medical Image Translation](https://mlsanity.com/paper/2305.14589/) (2023)
- [Function Space Bayesian Pseudocoreset for Bayesian Neural Networks](https://mlsanity.com/paper/2310.17852/) (2023)
- [Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation](https://mlsanity.com/paper/2403.02311/) (2024)
- [Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model](https://mlsanity.com/paper/2111.11055/) (2021)
- [Instance-wise Uncertainty for Class Imbalance in Semantic Segmentation](https://mlsanity.com/paper/2407.12609/) (2024)
- [Entropy Bootstrapping for Weakly Supervised Nuclei Detection](https://mlsanity.com/paper/2411.13528/) (2024)

## Abstract (arXiv)

As Deep Learning continues to yield successful applications in Computer Vision, the ability to quantify all forms of uncertainty is a paramount requirement for its safe and reliable deployment in the real-world. In this work, we leverage the formulation of variational inference in function space, where we associate Gaussian Processes (GPs) to both Bayesian CNN priors and variational family. Since GPs are fully determined by their mean and covariance functions, we are able to obtain predictive uncertainty estimates at the cost of a single forward pass through any chosen CNN architecture and for any supervised learning task. By leveraging the structure of the induced covariance matrices, we propose numerically efficient algorithms which enable fast training in the context of high-dimensional tasks such as depth estimation and semantic segmentation. Additionally, we provide sufficient conditions for constructing regression loss functions whose probabilistic counterparts are compatible with aleatoric uncertainty quantification.