AI Paper Atlas

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

A Probabilistic U-Net for Segmentation of Ambiguous Images

Simon Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R. Ledsam, Klaus Maier-Hein, S. M. Ali Eslami, Danilo Jimenez Rezende, Olaf Ronneberger

NeurIPS 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 151 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
Use a context-conditioned probabilistic latent prior and inject sampled latents late in the U-NetProbabilistic U-Net · LIDC-IDRI and Cityscapessquared GEDImproved
Use Probabilistic U-Net samples to distinguish ambiguous from unambiguous lesionsLIDC-IDRI · LIDC-IDRI test setambiguous-lesion discrimination accuracy: 0.699 -> 0.736Improved
Fix the prior to a standard Gaussian instead of conditioning it on the image (ablation)Probabilistic U-Net · LIDC-IDRI and Cityscapessquared GEDHurt
Fix the prior and remove the input image from the posterior (ablation)Probabilistic U-Net · LIDC-IDRI and Cityscapessquared GEDHurt
Inject latent features at the beginning rather than after the U-Net decoder (ablation)Probabilistic U-Net · LIDC-IDRI and Cityscapessquared GEDHurt
Inject latent features at the beginning rather than after the U-Net decoder (ablation)Probabilistic U-Net · multiple samplessquared GEDHurt
Increase the number of samples drawn from the modelProbabilistic U-Net · LIDC-IDRI test setsquared GED: 0.811 -> 0.388 -> 0.321 -> 0.287Improved
Increase the number of samples drawn from the modelProbabilistic U-Net · Cityscapes validation setsquared GED: 0.874 -> 0.337 -> 0.248 -> 0.206Improved

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