AI Paper Atlas

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

ICCV 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 3 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
add TopoMDCs (Stage 1) to baseline (ablation)TopoTTA · Retinal vessel average (UNet)Dice (%): 65.37 -> 68.70Improved
add TopoMDCs (Stage 1) to baseline (ablation)TopoTTA · Retinal vessel average (UNet)clDice (%): 61.69 -> 65.14Improved
add TopoMDCs (Stage 1) to baseline (ablation)TopoTTA · Retinal vessel average (UNet)Betti error: 82.24 -> 76.28Improved
add TopoHG (Stage 2) to teacher-student baseline (ablation)TopoTTA · Retinal vessel average (UNet)clDice (%): 62.20 -> 66.61Improved
add TopoHG (Stage 2) to teacher-student baseline (ablation)TopoTTA · Retinal vessel average (UNet)Dice (%): 65.95 -> 68.82Improved
add Stage 2 TopoHG on top of Stage 1 (ablation)TopoTTA · Retinal vessel average (UNet)clDice (%): 65.14 -> 67.81Improved
use all eight TopoMDCs instead of CDC only (ablation)TopoTTA · Retinal vessel average (UNet)Dice (%): 68.99 -> 69.87Improved
use all eight TopoMDCs instead of orthogonal only (ablation)TopoTTA · Retinal vessel average (UNet)clDice (%): 67.54 -> 67.81Improved
use low-frequency swap TopoHG instead of Gaussian noise (ablation)TopoTTA · Retinal vessel average (UNet)Dice (%): 68.48 -> 69.87Improved
use low-frequency swap TopoHG instead of spatial image swap (ablation)TopoTTA · Retinal vessel average (UNet)Dice (%): 67.65 -> 69.87Improved
replace low-frequency swap with spatial image swap in TopoHG (ablation)TopoTTA · Retinal vessel average (UNet)Betti error: 73.27 -> 69.63Mixed
use TopoTTA instead of CoTTAUNet, ten datasets · Average over ten pairsclDice (%): 69.34 -> 74.00Improved

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.

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

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