Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification

2023/03/23 by Kilian Zepf, Zepf, Kilian, Selma Wanna +13 · 1 citation
Computer Science · Medicine · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.2303.13123

openalex publication_date 2023/03/23 · openalex created_date 2023/03/25 · openalex updated_date 2026/08/03

Abstract

Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images. This is a common scenario in the medical domain due to variations in equipment, acquisition sites, or image corruptions. This work addresses the challenge of OOD detection by proposing Laplacian Segmentation Networks (LSN): methods which jointly model epistemic (model) and aleatoric (data) uncertainty for OOD detection. In doing so, we propose the first Laplace approximation of the weight posterior that scales to large neural networks with skip connections that have high-dimensional outputs. We demonstrate on three datasets that the LSN-modeled parameter distributions, in combination with suitable uncertainty measures, gives superior OOD detection.

Cited by

• Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching

Related

• An out-of-distribution discriminator based on Bayesian neural network epistemic uncertainty
• Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks
• On the Practicality of Deterministic Epistemic Uncertainty
• Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
• Distributional Uncertainty for Out-of-Distribution Detection