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

TL;DR

This paper introduces Layer Ensembles, a novel method for uncertainty estimation in deep learning segmentation that uses a single network and pass, reducing computational costs while maintaining competitive accuracy.

Contribution

The paper presents Layer Ensembles, a new single-pass uncertainty estimation technique that outperforms traditional methods requiring multiple models or passes.

Findings

Competitive results with state-of-the-art Deep Ensembles

Effective image-level uncertainty metric for segmentation

Reduces computational costs significantly

Abstract

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.