AI Paper Atlas

Research map / Detection and segmentation / CNN features

Topology-Aware Segmentation Using Discrete Morse Theory

Xiaoling Hu, Yusu Wang, Li Fuxin, Dimitris Samaras, Chao Chen

ICLR 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 14 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 DMT-loss instead of TopoLossU-Net segmentation on CREMI 2D · CREMI 2DBetti Error: 1.113 -> 0.982Improved
Use DMT-loss instead of TopoLosssegmentation networks · ISBI13 2DBetti Error: 1.253 ± 0.172 -> 1.102 ± 0.203Improved
Use DMT-loss instead of TopoLosssegmentation networks · CrackTreeBetti Error: 0.672 ± 0.176 -> 0.518 ± 0.189Improved
Use DMT-loss instead of TopoLosssegmentation networks · RoadBetti Error: 1.275 ± 0.192 -> 0.995 ± 0.301Improved
Use DMT-loss instead of TopoLoss3D segmentation networks · ISBI13 3DBetti Error: 0.972 ± 0.245 -> 0.812 ± 0.134Improved
Use DMT-loss instead of TopoLoss3D segmentation networks · CREMI 3DBetti Error: 1.076 ± 0.206 -> 0.726 ± 0.187Improved
Use DMT-loss instead of TopoLoss3D segmentation networks · 3DircadbBetti Error: 2.245 ± 0.255 -> 1.415 ± 0.305Improved
Set persistence threshold epsilon to 0.1 rather than 0.2 (ablation)DMT-loss · CREMI 2DBetti Error: 0.982 -> 1.206Hurt
Set persistence threshold epsilon to 0.3 rather than 0.2 (ablation)DMT-loss · CREMI 2DBetti Error: 0.982 -> 2.105Hurt
Set balanced-loss weight beta to 2 rather than 3 (ablation)DMT-loss · CREMI 2DBetti Error: 0.982 -> 1.074Hurt
Set balanced-loss weight beta to 4 rather than 3 (ablation)DMT-loss · CREMI 2DBetti Error: 0.982 -> 1.181Hurt
Use DMT-selected critical structures rather than generic reweighting of false-positive and false-negative pixelscross-entropy segmentation loss · CREMI 2DBetti Error: 2.753 vs. 0.982Improved

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