AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty

Miguel Monteiro, Loic Le Folgoc, Daniel Coelho de Castro, Nick Pawlowski, Bernardo Marques, Konstantinos Kamnitsas, Mark van der Wilk, Ben Glocker

NeurIPS 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 80 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
model correlated logit uncertainty with a low-rank covariance instead of independent pixel-wise uncertainty (ablation)SSN on LIDC-IDRI · LIDC-IDRI, one annotation setD²_GED: 0.734 ± 0.009 -> 0.365 ± 0.005Improved
model correlated logit uncertainty with a low-rank covariance instead of independent pixel-wise uncertainty (ablation)SSN on LIDC-IDRI · LIDC-IDRI, four annotation setsDSC (%): 37.0 ± 0.4 -> 43.6 ± 0.4Improved
train with all four expert annotations rather than one annotation set (ablation)SSN low-rank · LIDC-IDRIDSC (%): 40.7 ± 0.4 -> 43.6 ± 0.4Improved
increase label-map patch size from 30 mm³ to 60 mm³ (ablation)SSN low-rank · BraTS 2017DSC_WT (%): 88.0 ± 1.3 -> 88.7 ± 1.3No clear effect
increase label-map patch size from 30 mm³ to 60 mm³ (ablation)SSN low-rank · BraTS 2017D²_GED: 0.635 ± 0.029 -> 0.689 ± 0.031No clear effect
vary covariance rank above rank one (ablation)SSN low-rank · BraTS 2017performance metricsNo clear effect
use low-rank covariance rather than diagonal covariance (ablation)SSN on the toy problem · Toy problemlog-likelihood: -4.87 -> -0.93Improved
use stochastic low-rank logits rather than a deterministic networkSSN on BraTS 2017 · BraTS 2017DSC_WT (%): 88.2 ± 1.3 -> 88.0 ± 1.3No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy