AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

An OpenMind for 3D Medical Vision Self-supervised Learning

Tassilo Wald, Constantin Ulrich, Jonathan Suprijadi, Sebastian Ziegler, Michal Nohel, Robin Peretzke, Gregor Kohler, Klaus Maier-Hein

ICCV 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 26 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 MAE pre-training before fine-tuningResEnc-L CNN · OpenMind segmentation mean (150 epochs)mean DSC (%): 68.44 -> 70.91Improved
add MAE pre-training before fine-tuningPrimus-M Transformer · OpenMind segmentation mean (150 epochs)mean DSC (%): 63.62 -> 70.42Improved
add VoCo contrastive pre-trainingPrimus-M Transformer · OpenMind segmentation mean (150 epochs)mean DSC (%): 63.62 -> 57.61Hurt
add VoCo contrastive pre-trainingResEnc-L CNN · OpenMind segmentation mean (150 epochs)mean DSC (%): 68.44 -> 68.50No clear effect
add VoCo pre-trainingResEnc-L CNN · OpenMind classificationmean average precision (%): 62.97 -> 68.18Improved
add MAE pre-trainingResEnc-L CNN · OpenMind classificationmean average precision (%): 62.97 -> 63.57No clear effect
fine-tune CNN 1000 epochs instead of 150 (ablation)ResEnc-L CNN MAE · OpenMind segmentation meanmean DSC (%): 70.91 -> 71.63Improved
fine-tune CNN 1000 epochs instead of 150 (ablation)ResEnc-L CNN VoCo · OpenMind segmentation meanmean DSC (%): 68.50 -> 69.36Improved
freeze encoder during fine-tuning (vs default) (ablation)ResEnc-L CNN · OpenMind segmentation, 4 development datasetsaverage DSC (%): 76.15 -> 55.25Hurt
freeze encoder during fine-tuning (vs default) (ablation)Primus-M Transformer · OpenMind segmentation, 4 development datasetsaverage DSC (%): 68.36 -> 30.38Hurt
add Sawtooth fine-tuning schedule instead of default (ablation)ResEnc-L CNN · OpenMind segmentation, 4 development datasetsaverage DSC (%): 76.15 -> 76.60Improved
add warm-up to default fine-tuning (ablation)Primus-M Transformer · OpenMind segmentation, 4 development datasetsaverage DSC (%): 68.36 -> 68.76Improved

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