AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Persistent Homology With Improved Locality Information for More Effective Delineation

Doruk Öner, Adélie Garin, Mateusz Koziński, Kathryn P. Hess, Pascal Fua

TPAMI 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 9 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
replace thresholding filtration with combined threshold plus height-function filtrationPH-based topological loss (Homo-Reg) · Massachusetts (validation)APLS: 65.0 -> 68.7Improved
same change, Betti errorHomo-Reg · Massachusetts (validation)Betti error: 1.09 -> 0.90Improved
same change on RTracerHomo-Reg · RTracer (test)APLS: 69.9 -> 73.8Improved
same change on RTracer, Betti errorHomo-Reg · RTracer (test)Betti error: 1.07 -> 0.89Improved
same change on 3D NeuronsHomo-Reg · Neurons (3D, test)APLS: 85.4 -> 86.9Improved
same change on 3D BrainHomo-Reg · Brain (3D, test)APLS: 70.5 -> 73.4Improved
add PH-based topological loss (with our filtration) to U-Net MSE trainingU-Net · RTracer (test)Betti error: 2.99 -> 0.89Improved
add PH topological loss on distance maps instead of classification mapsHomo-Pre · Massachusetts (validation)APLS: 62.5 -> 65.0Improved
use ConnLoss instead of our PH lossdelineation network · RTracer (test)APLS: 73.8 -> 75.4Hurt
use ConnLoss instead of our PH loss, Betti errordelineation network · RTracer (test)Betti error: 0.89 -> 1.30Hurt
use new filtration when injecting synthetic errors (ablation)topological loss term C · synthetic distance mapsprobability loss decreases after injecting an error: 0.4 -> 0.2Improved

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