AI Paper Atlas

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

A Unified Visual Information Preservation Framework for Self-supervised Pre-training in Medical Image Analysis

Hong-Yu Zhou, Chixiang Lu, Chaoqi Chen, Sibei Yang, Yizhou Yu

TPAMI 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 90 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
remove skip connections (nsUNet) (ablation)PCRLv2 · NIH ChestX-ray (5% labels)mean AUROC: 75.4 -> 76.6Improved
remove skip connections (nsUNet) (ablation)PCRLv2 · BraTS (10% labels)Dice: 71.5 -> 73.0Improved
remove skip connections (nsUNet) (ablation)PCRLv2 · LiTS (10% labels)Dice: 77.6 -> 79.0Improved
use cross-scale instead of pairwise siamese comparison (ablation)PCRLv2 · NIH ChestX-ray (5% labels)mean AUROC: 76.6 -> 76.0Hurt
add feature comparison to pixel restoration (ablation)pixel restoration · BraTS WT/ET, NIH transferDice / AUROC: WT 74.2 -> 76.2, ET 64.9 -> 64.6, NIH 78.2 -> 80.9Improved
add pixel restoration to feature comparison (ablation)feature comparison · BraTS WT/ET, NIH transferDice / AUROC: WT 76.4 -> 76.2, ET 63.8 -> 64.6, NIH 78.5 -> 80.9Mixed
add 3 feature scales (ablation)Res+Comp · BraTS WT/ET, NIH transferDice / AUROC: WT 76.2 -> 76.9, ET 64.6 -> 66.1, NIH 80.9 -> 81.5Improved
increase scales from 3 to 5 (ablation)Res+Comp · BraTS WT/ET, NIH transferDice / AUROC: WT 76.9 -> 77.2, ET 66.1 -> 66.8, NIH 81.5 -> 82.0Improved
add multi-crop in 3D (ablation)Res+Comp, 5 scales · BraTS WT/ET, NIH transferDice / AUROC: NIH 82.0 -> 82.5, BraTS failMixed
replace multi-crop with sub-crop (ablation)Res+Comp, 5 scales · BraTS WT/ET, NIH transferDice / AUROC: WT 77.2 -> 77.7, ET 66.8 -> 67.2, NIH 82.0 -> 82.7Improved
PCRLv2 vs PCRLv1 (multi-scale, nsUNet, simpler design)PCRLv1 · NIH ChestX-ray semi-supervised (5% labels)mean AUROC: 74.1 -> 76.6Improved
PCRLv2 vs PCRLv1PCRLv1 · LiTS transfer (10% labels)Dice: 77.3 -> 79.0Improved

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