Research map / Learning theory and algorithms / Clustering
Topology Reconstruction of Tree-Like Structure in Images via Structural Similarity Measure and Dominant Set Clustering
Jianyang Xie, Yitian Zhao, Yonghuai Liu, Pan Su, Yifan Zhao, Jun Cheng, Yalin Zheng, Jiang Liu
Check 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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use curvilinear structural similarity-guided dominant-set clustering instead of the compared topology methods | Tree topology reconstruction · NeurB1 | DIADEM: 0.52 -> 0.67 | Improved |
| Use curvilinear structural similarity-guided dominant-set clustering instead of the compared topology methods | Tree topology reconstruction · NeurB2 | DIADEM: 0.26 -> 0.63 | Improved |
| Use the proposed topology reconstruction method instead of HSA | Tree topology reconstruction · RICE | absolute similarity (sa): 0.898 -> 0.921 | Improved |
| Use the proposed topology reconstruction method instead of HSA | Tree topology reconstruction · RICE | relative similarity (sr): 0.972 -> 0.984 | Improved |
| Use the proposed topology reconstruction method instead of HSA | Tree topology reconstruction · WIDE | parent similarity (sp): 0.966 -> 0.971 | Improved |
| Use the proposed topology reconstruction method instead of HSA | Tree topology reconstruction · WIDE | flow similarity (sf): 0.972 -> 0.980 | Improved |
| Use the proposed topology reconstruction method instead of HSA | Tree topology reconstruction · WIDE | absolute similarity (sa): 0.732 -> 0.788 | Improved |
| Use the proposed topology reconstruction method instead of HSA | Tree topology reconstruction · WIDE | relative similarity (sr): 0.860 -> 0.901 | Improved |
| Use the proposed method instead of the human observer reference | Tree topology reconstruction · WIDE | parent similarity (sp): 0.988 -> 0.971 | Hurt |
| Use the proposed method instead of the human observer reference | Tree topology reconstruction · WIDE | flow similarity (sf): 0.991 -> 0.980 | Hurt |
| Use the proposed method instead of the human observer reference | Tree topology reconstruction · WIDE | absolute similarity (sa): 0.826 -> 0.788 | Hurt |
| Use the proposed method instead of the human observer reference | Tree topology reconstruction · WIDE | relative similarity (sr): 0.940 -> 0.901 | Hurt |
Closest papers by meaning
- Topology-Reinforced Swin Transformer for Medical Image Analysis (NeurIPS 2026 · similarity 0.86)
- Reconstructing Evolving Tree Structures in Time Lapse Sequences by Enforcing Time-Consistency (TPAMI 2017 · similarity 0.86)
- Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss Function (AAAI 2025 · similarity 0.85)
- Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images (ICML 2024 · similarity 0.84)
- SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction (CVPR 2024 · similarity 0.84)
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (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.
