DeepAI AI Chat
Log In Sign Up

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

by   Alex Kendall, et al.
University of Cambridge

There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data. Traditionally it has been difficult to model epistemic uncertainty in computer vision, but with new Bayesian deep learning tools this is now possible. We study the benefits of modeling epistemic vs. aleatoric uncertainty in Bayesian deep learning models for vision tasks. For this we present a Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty. We study models under the framework with per-pixel semantic segmentation and depth regression tasks. Further, our explicit uncertainty formulation leads to new loss functions for these tasks, which can be interpreted as learned attenuation. This makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.


page 2

page 6

page 7


Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision

While Deep Neural Networks (DNNs) have become the go-to approach in comp...

Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning

Deep Learning (DL) methods have been transforming computer vision with i...

SLURP: Side Learning Uncertainty for Regression Problems

It has become critical for deep learning algorithms to quantify their ou...

A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications

Quantifying the uncertainty of supervised learning models plays an impor...

Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations

We present a deep learning method for single-station earthquake location...

Deep Deterministic Uncertainty for Semantic Segmentation

We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty...

Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction

Recent deep learning approaches focus on improving quantitative scores o...

Code Repositories


Implementation and evaluation of different approaches to get uncertainty in neural networks

view repo