AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Flow Stochastic Segmentation Networks

Fabio De Sousa Ribeiro, Omar Todd, Charles Jones, Avinash Kori, Raghav Mehta, Ben Glocker

ICCV 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 2 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 continuous-time flow instead of the SSN++ baselineFlow-SSN · LIDC-IDRID2_GED (M samples): 0.212 -> 0.182Improved
Use continuous-time flow instead of SSN++Flow-SSN · LIDC-IDRIDice: 0.471 -> 0.610Improved
Use discrete single-step IAF Flow-SSN instead of SSN++Flow-SSN · LIDC-IDRID2_GED (M samples): 0.212 -> 0.212No clear effect
Learn the base distribution (prior) instead of holding it fixed (ablation)Continuous Flow-SSN · LIDC-IDRIinference time: 5x reduction in inference timeImproved
Learn the prior so the flow network is much smaller (ablation)Continuous Flow-SSN · LIDC-IDRIparameters in flow network: 150K vs 14M paramsImproved
Reduce Euler ODE steps from 250 to 10 (ablation)Continuous Flow-SSN · LIDC-IDRID2_GED: T=10 competitiveNo clear effect
Increase Euler steps from 50 to 250 (ablation)Continuous Flow-SSN · LIDC-IDRID2_GED (16 samples): 0.210 -> 0.207No clear effect
Use Dopri5 adaptive solver instead of Euler T=250 (ablation)Continuous Flow-SSN · LIDC-IDRID2_GED (16 samples): 0.209 -> 0.207No clear effect
Use Flow-SSN instead of the SSN with low-rank covarianceFlow-SSN · MarkovShapesbits per dimension: outperforms all SSN variants, including full-rankImproved
Use low rank 2 SSN versus Flow-SSN (ablation)SSN · MarkovShapessample quality: rank 2 SSN hallucinates nonexistent shapesHurt
Increase MC samples from 16 to 512 (ablation)Discrete Flow-SSN · REFUGE-MultiRater optic cupD2_GED: 0.116 -> 0.081Improved
Increase MC samples from 16 to 512 (ablation)Discrete Flow-SSN · REFUGE-MultiRater optic cupHM-IoU: 0.766 -> 0.881Improved

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