Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for Segmentation

03/16/2022
by   Kaisar Kushibar, et al.
0

Uncertainty estimation in deep learning has become a leading research field in medical image analysis due to the need for safe utilisation of AI algorithms in clinical practice. Most approaches for uncertainty estimation require sampling the network weights multiple times during testing or training multiple networks. This leads to higher training and testing costs in terms of time and computational resources. In this paper, we propose Layer Ensembles, a novel uncertainty estimation method that uses a single network and requires only a single pass to estimate predictive uncertainty of a network. Moreover, we introduce an image-level uncertainty metric, which is more beneficial for segmentation tasks compared to the commonly used pixel-wise metrics such as entropy and variance. We evaluate our approach on 2D and 3D, binary and multi-class medical image segmentation tasks. Our method shows competitive results with state-of-the-art Deep Ensembles, requiring only a single network and a single pass.

READ FULL TEXT

page 5

page 9

page 14

page 15

page 16

research
06/21/2021

Distilling effective supervision for robust medical image segmentation with noisy labels

Despite the success of deep learning methods in medical image segmentati...
research
03/17/2023

Uncertainty-informed Mutual Learning for Joint Medical Image Classification and Segmentation

Classification and segmentation are crucial in medical image analysis as...
research
07/13/2021

What classifiers know what they don't?

Being uncertain when facing the unknown is key to intelligent decision m...
research
12/04/2020

Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification

Bayesian neural networks (BNNs) have been long considered an ideal, yet ...
research
06/15/2020

Depth Uncertainty in Neural Networks

Existing methods for estimating uncertainty in deep learning tend to req...
research
03/14/2023

Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models

Deep Ensembles are a simple, reliable, and effective method of improving...
research
10/29/2021

Deep Deterministic Uncertainty for Semantic Segmentation

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

Please sign up or login with your details

Forgot password? Click here to reset