AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Progressive Test Time Energy Adaptation for Medical Image Segmentation

Xiaoran Zhang, Byung-Woo Hong, Hyoungseob Park, Daniel H. Pak, Anne-Marie Rickmann, Lawrence H. Staib, James S. Duncan, Alex Wong

ICCV 2025 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 4 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 progressive energy-based TTApretrained UNet · ACDC to LVQuant LVDSC (%): 58.98 -> 76.93Improved
add progressive energy-based TTApretrained UNet · ACDC to M&M LVDSC (%): 47.69 -> 61.84Improved
add progressive energy-based TTApretrained UNet · M&M to ACDC LVDSC (%): 40.84 -> 59.97Improved
use energy TTA instead of TEAUNet TTA · ACDC to LVQuant LVDSC (%): 67.96 -> 76.93Improved
use energy TTA instead of TEAMedNeXt TTA · ACDC to LVQuant LVDSC (%): 75.85 -> 76.22Improved
use energy TTA instead of TEATTA on GMSC · GMSC spinal cord avgDSC (%): 77.3 -> 80.9Improved
use energy TTA instead of InTENTTTA on CHN lung · CHN to MCU/JSRT avgDSC (%): 95.9 -> 96.2Improved
add adversarial perturbations for energy-model negatives (ablation)energy model · ACDC to LVQuant LVDSC (%): 64.72 -> 76.93Improved
add spatial augmentation for energy-model negatives (ablation)energy model · ACDC to LVQuant LVDSC (%): 76.15 -> 76.93Improved
increase adaptation iterations from 1 to 10 (ablation)energy TTA · ACDC to LVQuant LVDSC (%): 64.85 -> 76.93Improved
reduce batch size from 4 to 1 (ablation)energy TTA · GMSC 1 to 3DSC (%): 77.7 -> 83.5No clear effect

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