Research map / Label-efficient and robust learning / Test-time adaptation
TopoTTA: Topology-Enhanced Test-Time Adaptation for Tubular Structure Segmentation
Jiale Zhou, Wenhan Wang, Shikun Li, Xiaolei Qu, Xin Guo, Yizhong Liu, Wenzhong Tang, Xun Lin, Yefeng Zheng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add TopoMDCs (Stage 1) to baseline (ablation) | TopoTTA · Retinal vessel average (UNet) | Dice (%): 65.37 -> 68.70 | Improved |
| add TopoMDCs (Stage 1) to baseline (ablation) | TopoTTA · Retinal vessel average (UNet) | clDice (%): 61.69 -> 65.14 | Improved |
| add TopoMDCs (Stage 1) to baseline (ablation) | TopoTTA · Retinal vessel average (UNet) | Betti error: 82.24 -> 76.28 | Improved |
| add TopoHG (Stage 2) to teacher-student baseline (ablation) | TopoTTA · Retinal vessel average (UNet) | clDice (%): 62.20 -> 66.61 | Improved |
| add TopoHG (Stage 2) to teacher-student baseline (ablation) | TopoTTA · Retinal vessel average (UNet) | Dice (%): 65.95 -> 68.82 | Improved |
| add Stage 2 TopoHG on top of Stage 1 (ablation) | TopoTTA · Retinal vessel average (UNet) | clDice (%): 65.14 -> 67.81 | Improved |
| use all eight TopoMDCs instead of CDC only (ablation) | TopoTTA · Retinal vessel average (UNet) | Dice (%): 68.99 -> 69.87 | Improved |
| use all eight TopoMDCs instead of orthogonal only (ablation) | TopoTTA · Retinal vessel average (UNet) | clDice (%): 67.54 -> 67.81 | Improved |
| use low-frequency swap TopoHG instead of Gaussian noise (ablation) | TopoTTA · Retinal vessel average (UNet) | Dice (%): 68.48 -> 69.87 | Improved |
| use low-frequency swap TopoHG instead of spatial image swap (ablation) | TopoTTA · Retinal vessel average (UNet) | Dice (%): 67.65 -> 69.87 | Improved |
| replace low-frequency swap with spatial image swap in TopoHG (ablation) | TopoTTA · Retinal vessel average (UNet) | Betti error: 73.27 -> 69.63 | Mixed |
| use TopoTTA instead of CoTTA | UNet, ten datasets · Average over ten pairs | clDice (%): 69.34 -> 74.00 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TENT — Tent: Fully Test-Time Adaptation by Entropy Minimization (ICLR 2021) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation (ICCV 2023 · similarity 0.88)
- Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation (TPAMI 2026 · similarity 0.88)
- Segmentation of Tubular Structures Using Iterative Training with Tailored Samples (ICCV 2023 · similarity 0.87)
- GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs (NeurIPS 2024 · similarity 0.86)
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.85)
- TopoDiffusionNet: A Topology-aware Diffusion Model (ICLR 2025 · similarity 0.85)
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.
