Research map / Detection and segmentation / CNN features
Topology-Preserving Deep Image Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · ISBI12 | Betti Error: 2.785 -> 0.429 | Helped |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · ISBI13 | Betti Error: 2.952 -> 1.253 | Helped |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · CREMI | Betti Error: 1.973 -> 1.113 | Helped |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · DRIVE | Betti Error: 2.784 -> 1.076 | Helped |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · CrackTree | Betti Error: 1.045 -> 0.672 | Helped |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · Road | Betti Error: 2.781 -> 1.275 | Helped |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · ISBI12 | Accuracy: 0.9678 -> 0.9626 | Hurt |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · ISBI13 | Accuracy: 0.9642 -> 0.9569 | Hurt |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · CREMI | Accuracy: 0.9498 -> 0.9456 | Hurt |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · DRIVE | Accuracy: 0.9549 -> 0.9521 | Hurt |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · CrackTree | Accuracy: 0.9854 -> 0.9826 | Hurt |
| Add the persistent-homology topological loss to cross-entropy training | TopoNet · Road | Accuracy: 0.9786 -> 0.9728 | Hurt |
Closest papers by meaning
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.91)
- Structure-Aware Image Segmentation with Homotopy Warping (NeurIPS 2022 · similarity 0.91)
- Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes (ICML 2023 · similarity 0.90)
- Towards Scalable Topological Regularizers (ICLR 2025 · similarity 0.84)
- Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss Function (AAAI 2025 · similarity 0.84)
- TopoDiffusionNet: A Topology-aware Diffusion Model (ICLR 2025 · similarity 0.84)
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.